© 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. 22-GEMMASCOPE-RES-131K
    7. 15744
    Prev
    Next
    INDEX
    Explanations

    titles, code statements

    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
     Maybe
    -1.12
     Perhaps
    -0.98
     vielleicht
    -0.93
     to
    -0.91
     maybe
    -0.89
    Zubereitung
    -0.88
     béisbol
    -0.85
    osidad
    -0.84
    pasar
    -0.83
    рп
    -0.83
    POSITIVE LOGITS
    each
    1.05
    แผ
    1.01
    else
    0.93
    increase
    0.90
    mathrm
    0.90
    每
    0.88
    errorMessage
    0.87
    PROV
    0.87
    Each
    0.85
    enumi
    0.85
    Activations Density 0.000%

    No Known Activations