© 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. 40046
    Prev
    Next
    INDEX
    Explanations

    places and their limits

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

    services, features, capabilities

    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
    唏
    0.47
     इंट्रोडक्शन
    0.45
     ireo
    0.45
    伝える
    0.45
     বেশকিছু
    0.43
    нию
    0.43
     paraît
    0.43
     मैटर
    0.43
    㥉
    0.43
    रातील
    0.42
    POSITIVE LOGITS
    ’
    0.52
    horn
    0.50
     chosen
    0.49
    chosen
    0.47
     used
    0.46
    qua
    0.45
     выбран
    0.45
    ，
    0.45
    ol
    0.44
    bin
    0.44
    Activations Density 0.000%

    No Known Activations