© 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. 33653
    Prev
    Next
    INDEX
    Explanations

    time one statistics

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

    React component lifecycle and state management

    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
    cloak
    0.41
    রাগ
    0.41
     PhD
    0.40
    统一
    0.40
    瀟
    0.39
    হাত
    0.39
    মিন
    0.39
    𝕠
    0.38
    Ле
    0.37
    名为
    0.37
    POSITIVE LOGITS
     Wikiseite
    0.44
     horrifying
    0.43
     څرنګوالی
    0.43
     gewesen
    0.43
     محکمہ
    0.43
     داشته
    0.43
     afect
    0.42
     jeopardize
    0.42
     afectar
    0.42
     घटने
    0.41
    Activations Density 0.000%

    No Known Activations