© 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. 126877
    Prev
    Next
    INDEX
    Explanations

    christ who, before grey, sample (, via info, proven innocent

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

    Seek advice, moral weight

    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
    एँ
    0.50
    와
    0.50
    일
    0.45
    esercizio
    0.45
    쿵
    0.44
    である
    0.43
    liess
    0.43
    istic
    0.43
    й
    0.43
    acide
    0.42
    POSITIVE LOGITS
    其他人
    0.49
     inboard
    0.48
     foco
    0.47
     ihtiyaç
    0.46
     aliv
    0.45
     schop
    0.44
     industrie
    0.44
     aque
    0.44
     ludzi
    0.43
     investir
    0.43
    Activations Density 0.005%

    No Known Activations