© 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. 221618
    Prev
    Next
    INDEX
    Explanations

    published, uploaded, intervals

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

    negative gradient and status

    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
    t
    0.52
     MOBILE
    0.50
    গ
    0.50
     dims
    0.46
     ит
    0.46
     तुरु
    0.45
     recv
    0.45
    s
    0.45
     MOTOR
    0.44
     cds
    0.43
    POSITIVE LOGITS
    щи
    0.47
    スター
    0.46
    {|\
    0.45
    াবদ্ধ
    0.44
     غير
    0.42
    міна
    0.42
    ঞ্জেল
    0.42
    setKeepCallback
    0.41
    getHost
    0.41
     zásobníku
    0.41
    Activations Density 0.001%

    No Known Activations