© 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. 78611
    Prev
    Next
    INDEX
    Explanations

    all followed by descriptor

    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
    チック
    -0.88
    ய்
    -0.79
    Ping
    -0.79
    semana
    -0.79
     alas
    -0.79
     notepad
    -0.78
     Argentina
    -0.77
    怎么做
    -0.77
    RETT
    -0.77
    所有人都
    -0.77
    POSITIVE LOGITS
     their
    1.41
     probability
    1.30
     its
    1.30
     likelihood
    1.26
     honesty
    1.20
     fairness
    1.17
     senses
    1.11
     seriousness
    1.08
    probability
    1.00
     our
    0.99
    Activations Density 0.017%

    No Known Activations