© 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. 47215
    Prev
    Next
    INDEX
    Explanations

    Company obligations

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

    shutil module operations

    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
    ორი
    0.43
    eqa
    0.42
    ៉
    0.42
    τρ
    0.40
    jeća
    0.39
    wallepics
    0.39
    წყვე
    0.39
    unarod
    0.39
    ადი
    0.38
    라
    0.38
    POSITIVE LOGITS
     moved
    0.52
     Inquisition
    0.51
     Translation
    0.49
     possiamo
    0.47
     malah
    0.47
     DMV
    0.47
     aspirated
    0.45
     remission
    0.45
     збіль
    0.45
     ampliamente
    0.45
    Activations Density 0.000%

    No Known Activations