© 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. 202395
    Prev
    Next
    INDEX
    Explanations

    dumpster rental

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

    your secret recording session

    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
     Garant
    0.48
     Bit
    0.45
    ালক
    0.45
    値下げ
    0.44
    綑
    0.44
     直接
    0.44
    重大
    0.43
    例外
    0.43
    旗
    0.43
    телей
    0.42
    POSITIVE LOGITS
    above
    0.47
    ujący
    0.45
    芗
    0.45
    izzazione
    0.44
    zare
    0.44
    izarea
    0.44
    booked
    0.43
    શ
    0.43
    ona
    0.42
    rocchia
    0.42
    Activations Density 0.001%

    No Known Activations