© 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. 117185
    Prev
    Next
    INDEX
    Explanations

    introduction to

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

    This neuron fires on high-level document labels or genre/section words (e.g. “Introduction,” “Sequel,” “Guide,” “Ode,” “Response,” etc.).

    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
    To
    -1.43
    ของ
    -1.33
     kepada
    -1.27
     onto
    -1.23
     To
    -1.02
    จาก
    -1.02
     unto
    -1.01
     către
    -1.01
     vnto
    -0.97
     TO
    -0.96
    POSITIVE LOGITS
     unz
    0.90
     Noir
    0.89
     MAGAZINE
    0.89
    があ
    0.86
     JEAN
    0.85
     Prancis
    0.85
    ائل
    0.84
     اکنون
    0.84
     tredje
    0.84
    🤬
    0.83
    Activations Density 0.129%

    No Known Activations