© 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. 64698
    Prev
    Next
    INDEX
    Explanations

    documentation section headers

    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
    內容簡介
    -1.47
     subjek
    -1.38
     kalori
    -1.36
     Organizador
    -1.34
     seraient
    -1.31
     alkoh
    -1.30
     radikal
    -1.30
     induk
    -1.30
    brücken
    -1.30
     Sosial
    -1.30
    POSITIVE LOGITS
    ,
    1.72
    Note
    1.71
    It
    1.68
     may
    1.61
    V
    1.52
     Note
    1.48
    </em>
    1.47
     c
    1.45
    v
    1.44
     used
    1.39
    Activations Density 0.012%

    No Known Activations