© 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. 141739
    Prev
    Next
    INDEX
    Explanations

    subscription and services

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

    problem descriptions

    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
     célula
    0.57
     عنصر
    0.53
     bioqu
    0.52
    妊娠
    0.51
     mastect
    0.50
     moléculas
    0.50
    츨
    0.50
     células
    0.50
     hücre
    0.50
     influencia
    0.49
    POSITIVE LOGITS
    f
    0.66
    v
    0.56
     Forever
    0.55
    s
    0.54
     Voice
    0.54
    m
    0.52
    lc
    0.52
    smart
    0.50
    l
    0.49
    3
    0.49
    Activations Density 0.001%

    No Known Activations