© 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. 150873
    Prev
    Next
    INDEX
    Explanations

    . codes

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

    technical descriptions and instructions

    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
     வெறும்
    0.48
     వే
    0.48
     journe
    0.48
    ございました
    0.47
     doğum
    0.47
     cele
    0.47
    缤
    0.47
     libertarian
    0.46
     leftist
    0.45
     కనిప
    0.45
    POSITIVE LOGITS
    ac
    0.48
    psis
    0.47
    ̓
    0.47
    rural
    0.46
    Outdoor
    0.45
    事は
    0.45
    probable
    0.44
    cka
    0.44
    y
    0.44
    oto
    0.43
    Activations Density 0.001%

    No Known Activations