© 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. 131283
    Prev
    Next
    INDEX
    Explanations

    dwells in, entrance to

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

    parenthetical phrases

    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
     Significantly
    0.46
    範圍
    0.45
    犮
    0.44
     થ
    0.44
     Barbados
    0.43
     マイ
    0.43
    埥
    0.42
    bg
    0.42
     休
    0.42
    ગ
    0.42
    POSITIVE LOGITS
     síntomas
    0.56
    oarece
    0.55
     primeira
    0.52
     produt
    0.50
     calidad
    0.49
     oczywiście
    0.49
     células
    0.49
     curvas
    0.49
     neuralgia
    0.48
     sequel
    0.48
    Activations Density 0.000%

    No Known Activations