© 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. 204170
    Prev
    Next
    INDEX
    Explanations

    on backorder, ships soon

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

    easy to, you don't, time()

    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
     الأمر
    0.42
    <0xE3>
    0.42
    ylabel
    0.42
    r
    0.41
    ্যায়
    0.41
    Supports
    0.41
    ickers
    0.40
     NotImplemented
    0.40
    妩
    0.40
    ω
    0.39
    POSITIVE LOGITS
    는
    0.54
    は
    0.53
    通常の
    0.49
    들을
    0.47
     ждут
    0.47
    риев
    0.46
    crisis
    0.46
    浜
    0.46
     koris
    0.45
    हार्
    0.45
    Activations Density 0.001%

    No Known Activations