© 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. 222334
    Prev
    Next
    INDEX
    Explanations

    consumption and service intervals

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

    releases, merges, converts into

    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
    കുന്ന
    0.55
    χρο
    0.52
    Per
    0.51
     enfoc
    0.51
     centred
    0.51
    ζα
    0.51
    4
    0.51
     .
    0.50
     formula
    0.50
    パー
    0.50
    POSITIVE LOGITS
    oping
    0.52
     акысыз
    0.48
     प्रदर्शन
    0.48
    🥴
    0.47
    ính
    0.47
     स्वस्थ
    0.47
    adakan
    0.46
     ආකාර
    0.46
    ul
    0.46
     poseen
    0.46
    Activations Density 0.001%

    No Known Activations