© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11184
    Prev
    Next
    INDEX
    Explanations

    pack, thought, train, coating, romper, work

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

    web addresses

    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_40_width_16k_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
     Cabinet
    0.38
     ‬
    0.38
    AsUp
    0.35
     Lorem
    0.35
    hiba
    0.35
     wt
    0.35
    Cabinet
    0.35
     에서
    0.34
     Again
    0.34
     Either
    0.34
    POSITIVE LOGITS
     Pochettino
    0.43
    haltens
    0.41
    ických
    0.41
    <0x93>
    0.40
    icester
    0.38
    aching
    0.38
    ifices
    0.38
    Ђ
    0.38
    ஸல்
    0.37
    CGPoint
    0.36
    Activations Density 0.034%

    No Known Activations