© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 21148
    Prev
    Next
    INDEX
    Explanations

    wider world, commercially made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wxr
    0.57
    startTimestamp
    0.49
    ྛ
    0.47
    ifically
    0.46
    э
    0.46
     Cognito
    0.45
    ೂರ್ವ
    0.45
    omyc
    0.45
    timestamps
    0.45
     Gasoline
    0.45
    POSITIVE LOGITS
    (,
    0.53
    به
    0.52
    オンライン
    0.52
     متر
    0.51
    _{
    0.50
    Α
    0.49
    メートル
    0.49
    ト
    0.49
    モード
    0.49
    İ
    0.49
    Activations Density 0.000%

    No Known Activations