© 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. 158700
    Prev
    Next
    INDEX
    Explanations

    descriptive information and locations

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

    language or code blocks

    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
    ing
    0.52
    ant
    0.47
    ံ
    0.47
    intensité
    0.44
    ng
    0.43
    픈
    0.42
    antile
    0.42
    att
    0.42
    ंबा
    0.42
    马
    0.42
    POSITIVE LOGITS
     dosing
    0.45
    عود
    0.45
     আবারো
    0.43
    examtype
    0.43
     শের
    0.43
    つの
    0.42
    சரி
    0.42
    Shader
    0.42
     regrett
    0.42
    reeting
    0.41
    Activations Density 0.000%

    No Known Activations