© 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. 28102
    Prev
    Next
    INDEX
    Explanations

    months and specific non-english scripts

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

    making amphetamine, social, specific

    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
    Bol
    0.55
    {
    0.54
    "
    0.52
    Fantastic
    0.51
    im
    0.50
    •
    0.47
     पड
    0.46
    গ্রহ
    0.46
    *
    0.45
    ग्रह
    0.44
    POSITIVE LOGITS
     ಯು
    0.59
     කා
    0.55
     入り
    0.55
     通勤
    0.55
     နှင့်
    0.54
     അയ
    0.53
     державної
    0.52
     журнал
    0.52
     ಪೊಲೀ
    0.51
     思い
    0.51
    Activations Density 0.000%

    No Known Activations