© 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. 63696
    Prev
    Next
    INDEX
    Explanations

    implements, Q:, Perimeter Institute

    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
    dekat
    -0.86
     霜
    -0.82
     its
    -0.82
     perdita
    -0.79
    سك
    -0.77
     MED
    -0.77
     protegida
    -0.76
    ⼀
    -0.75
     compartida
    -0.75
    телна
    -0.75
    POSITIVE LOGITS
    AppMethodBeat
    0.98
    empre
    0.84
    ¿½
    0.83
    好像
    0.82
    mployed
    0.82
    möglichkeiten
    0.81
    istisches
    0.81
    eated
    0.81
    Topo
    0.80
    varet
    0.80
    Activations Density 0.000%

    No Known Activations