© 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. 78892
    Prev
    Next
    INDEX
    Explanations

    license and copyright 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_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
    DIPSETTING
    -0.79
    scryfall
    -0.76
    Humph
    -0.71
    setTypeface
    -0.69
     отлича
    -0.69
    kulum
    -0.68
    仇
    -0.68
     AGA
    -0.65
    ほう
    -0.65
    Ссылки
    -0.65
    POSITIVE LOGITS
    containsKey
    0.88
     diag
    0.82
    Formation
    0.79
    tsk
    0.77
    jessica
    0.77
    slika
    0.76
    radan
    0.75
     tieto
    0.75
    >%
    0.74
    rabbitmq
    0.74
    Activations Density 0.050%

    No Known Activations