© 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. 78154
    Prev
    Next
    INDEX
    Explanations

    geeks

    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
     murale
    -1.09
     kampen
    -1.07
     hadas
    -1.04
     kalender
    -1.04
     långt
    -1.04
    Ѕ
    -1.04
     alkot
    -1.04
    KOV
    -1.02
    Ħ
    -1.02
     tevé
    -1.01
    POSITIVE LOGITS
     and
    1.13
     be
    0.98
    http
    0.97
    4
    0.92
     http
    0.89
    9
    0.89
    人和
    0.88
    ©
    0.87
    頌
    0.86
    https
    0.85
    Activations Density 0.118%

    No Known Activations