© 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. 27708
    Prev
    Next
    INDEX
    Explanations

    functioning of systems

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

    system functioning and viability

    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
     উদ্দেশ্য
    0.45
     amacı
    0.44
     sviluppo
    0.44
     exclusivement
    0.44
     trifling
    0.43
    𓐄
    0.43
    憉
    0.42
     $*
    0.42
    ပြု
    0.42
    ."',
    0.42
    POSITIVE LOGITS
    Gonz
    0.57
    Assets
    0.50
    Records
    0.50
    you
    0.47
    Adapt
    0.46
    Guardian
    0.46
    Parliament
    0.46
    Archives
    0.46
    Hosting
    0.45
    고
    0.45
    Activations Density 0.001%

    No Known Activations