© 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. 219647
    Prev
    Next
    INDEX
    Explanations

    endings or specific nouns

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

    writing and information sources

    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
    iale
    0.52
    㳖
    0.50
     risultato
    0.50
    ateur
    0.49
    uaire
    0.48
    ampionship
    0.46
    λού
    0.46
    iseren
    0.46
    ruire
    0.46
    テー
    0.45
    POSITIVE LOGITS
    樂
    0.45
     пункта
    0.42
     എ
    0.41
    бр
    0.41
     vybaven
    0.41
     porosity
    0.40
    বিধান
    0.39
    bra
    0.39
     wave
    0.39
    씽
    0.39
    Activations Density 0.000%

    No Known Activations