© 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. 204042
    Prev
    Next
    INDEX
    Explanations

    press release identifier after slash

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

    Angular component declaration

    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
    스
    0.49
    スタイル
    0.47
     گذشته
    0.47
     सराह
    0.46
    bleshooting
    0.45
    력
    0.45
    ्र
    0.45
     प्रशंसा
    0.44
     обслуживание
    0.44
    𝙱
    0.44
    POSITIVE LOGITS
     Croydon
    0.50
     Clermont
    0.47
     Hertfordshire
    0.47
     Colchester
    0.47
     Brentwood
    0.47
     Clarendon
    0.46
    ঘাত
    0.44
     Crawley
    0.44
     పేర్కొ
    0.43
    দশ
    0.42
    Activations Density 0.000%

    No Known Activations