© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63346
    Prev
    Next
    INDEX
    Explanations

    alternatives and contrasts

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to extremely common “function” words (short high-frequency tokens like to, of, the, its, so, and similar stopwords).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Affect
    -1.09
    віду
    -1.02
     zwar
    -1.00
    HAPPY
    -1.00
     AFFECT
    -1.00
    三浦
    -0.99
     insuffisamment
    -0.99
     affecting
    -0.96
    这种情况
    -0.96
     inept
    -0.96
    POSITIVE LOGITS
     conversely
    1.41
     наоборот
    1.02
    También
    1.01
    กลับ
    0.98
     caution
    0.97
     curse
    0.96
     altrett
    0.95
     alternatively
    0.95
    相反
    0.95
    Cuando
    0.92
    Activations Density 0.078%

    No Known Activations