© 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. 34-GEMMASCOPE-RES-131K
    4. 107367
    Prev
    Next
    INDEX
    Explanations

    claim bonus offers

    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_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
     Skin
    -0.82
     разли
    -0.79
     ня
    -0.75
     Veterinary
    -0.73
     אני
    -0.73
    :///
    -0.73
     Fishing
    -0.72
     gratitude
    -0.72
    ӳ
    -0.71
    subaru
    -0.71
    POSITIVE LOGITS
    claim
    1.05
    在我们
    1.02
    CLAIM
    0.97
     claim
    0.95
     our
    0.94
    Claim
    0.94
    我們
    0.93
    我们
    0.93
     проверить
    0.92
    ственный
    0.90
    Activations Density 0.010%

    No Known Activations