© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27657
    Prev
    Next
    INDEX
    Explanations

    comparison and states

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

    The neuron flags terms naming control or baseline treatment conditions (e.g. placebo, without, “supportive care,” “solutions,” “control,” “alone,” 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_22/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
     leave
    -0.86
    normally
    -0.79
     edits
    -0.78
    ditionally
    -0.78
     анализ
    -0.77
     edit
    -0.77
    licet
    -0.76
    材
    -0.75
    frid
    -0.75
    HOLY
    -0.75
    POSITIVE LOGITS
     både
    1.00
     Improved
    0.93
    GetLength
    0.89
     improved
    0.88
    both
    0.84
     olduk
    0.82
    asjon
    0.81
    ัฒ
    0.79
    impro
    0.78
     蛇
    0.78
    Activations Density 0.058%

    No Known Activations