© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107489
    Prev
    Next
    INDEX
    Explanations

    the followed by common nouns

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases about issues, types, and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OO
    0.54
    Materials
    0.52
    材料
    0.50
    禹
    0.47
    RENGTH
    0.47
    Amp
    0.46
    Joke
    0.45
    WHO
    0.44
    HU
    0.44
    ()(
    0.43
    POSITIVE LOGITS
     lungo
    0.55
    ก
    0.53
     optimisation
    0.52
     duelo
    0.52
     grafo
    0.50
     hunting
    0.50
     colon
    0.49
     preparar
    0.47
     contratos
    0.47
     escenario
    0.46
    Activations Density 0.000%

    No Known Activations