© 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. 219268
    Prev
    Next
    INDEX
    Explanations

    internationalized text or varied script

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

    phrases introducing topics

    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
    amme
    0.46
    u
    0.46
    ش
    0.45
    وه
    0.44
    et
    0.44
    ap
    0.44
    h
    0.43
     ghost
    0.43
    amphetamine
    0.42
    hook
    0.42
    POSITIVE LOGITS
    <unused226>
    0.57
    <unused726>
    0.56
    鸪
    0.55
     éché
    0.54
    <unused669>
    0.54
     取っ
    0.53
    <unused685>
    0.53
    ８
    0.52
    <unused1040>
    0.52
     αυτές
    0.51
    Activations Density 0.001%

    No Known Activations