© 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. 130667
    Prev
    Next
    INDEX
    Explanations

    years ago and since

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

    fundamental beliefs or aspects

    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
    مانی
    0.53
    AndUpdate
    0.50
    したい
    0.49
     lancéolées
    0.48
     PlayerSelector
    0.48
    عنی
    0.47
     করলাম
    0.47
    钥
    0.47
    ویل
    0.47
    ে
    0.46
    POSITIVE LOGITS
    mann
    0.55
    ord
    0.55
    man
    0.54
    ana
    0.52
    acea
    0.50
    mö
    0.49
    ond
    0.49
    mert
    0.49
    ang
    0.48
    [
    0.48
    Activations Density 0.000%

    No Known Activations