© 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. 64307
    Prev
    Next
    INDEX
    Explanations

    word or Microsoft Word documents

    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
     отметить
    -0.84
    DataURL
    -0.79
     Haare
    -0.77
    花粉
    -0.77
    degradation
    -0.77
     educate
    -0.77
     двой
    -0.77
    ૧
    -0.77
     Biophys
    -0.76
    Einen
    -0.76
    POSITIVE LOGITS
    そうです
    0.79
    uszki
    0.76
     Gallimard
    0.73
     drago
    0.71
    至今
    0.70
    !!!)
    0.70
    poses
    0.69
     tsk
    0.69
     OBL
    0.68
     pared
    0.68
    Activations Density 0.015%

    No Known Activations