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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12539
    Prev
    Next
    INDEX
    Explanations

    legal citations and years

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    んでしょう
    -1.02
    astero
    -1.00
     Про
    -0.99
     écoulé
    -0.98
    uterie
    -0.93
     белом
    -0.91
    terus
    -0.91
    𓆟
    -0.91
     and
    -0.90
    ₿
    -0.89
    POSITIVE LOGITS
     לכם
    1.09
    Détails
    1.02
    が多く
    1.00
    も多く
    0.99
     garantis
    0.95
     أيضا
    0.95
    know
    0.92
    Jeudi
    0.91
     natur
    0.91
    Vendredi
    0.91
    Activations Density 0.023%

    No Known Activations