© 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. 186563
    Prev
    Next
    INDEX
    Explanations

    foreign languages or scripts

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

    identifying details and responsibilities

    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
    F
    0.45
    FA
    0.45
     F
    0.42
    鹦
    0.42
    Orig
    0.42
    فرق
    0.41
     formule
    0.39
     histori
    0.39
     Ransom
    0.39
    岃
    0.39
    POSITIVE LOGITS
    ။
    0.52
    𝙩
    0.52
     ersten
    0.51
    焼け
    0.50
    숨
    0.50
     подели
    0.50
    ıştı
    0.49
    気に
    0.49
    摩
    0.49
     einzigen
    0.48
    Activations Density 0.000%

    No Known Activations