© 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. 100627
    Prev
    Next
    INDEX
    Explanations

    categories and types

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

    find out

    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
    <unused29>
    0.45
     పరిస్థ
    0.44
    домо
    0.42
     వారికి
    0.42
     ప్రేక్షకు
    0.41
    ప్రత్యర్థి
    0.41
     ponencia
    0.41
     магистра
    0.41
    ⦖
    0.41
     方
    0.41
    POSITIVE LOGITS
     this
    0.50
     NASA
    0.50
     to
    0.48
     Tok
    0.47
    are
    0.47
     our
    0.46
     diese
    0.46
    ↵
    0.45
     sono
    0.45
    یه
    0.45
    Activations Density 0.003%

    No Known Activations