© 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. 189230
    Prev
    Next
    INDEX
    Explanations

    programs, insurance, canisters, software

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

    executing software malfunctions

    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
     Ս
    0.52
    אם
    0.49
    一样的
    0.48
     אם
    0.48
     टी
    0.48
    ћин
    0.47
    ३
    0.47
    Jeśli
    0.46
    לו
    0.46
     deported
    0.46
    POSITIVE LOGITS
    ing
    0.63
    writing
    0.52
    r
    0.49
    interaction
    0.49
    en
    0.48
    ization
    0.47
    igraphic
    0.47
    ependent
    0.46
    as
    0.45
    ratic
    0.44
    Activations Density 0.001%

    No Known Activations