© 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. 203356
    Prev
    Next
    INDEX
    Explanations

    numbers and common words

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

    facial recognition and examples

    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
    managerpage
    0.46
     zaměst
    0.46
    完全
    0.45
    केंसी
    0.45
    治
    0.44
    徝
    0.44
    чої
    0.44
    聁
    0.43
    手里
    0.43
    ੂ
    0.43
    POSITIVE LOGITS
    ↵
    0.61
    al
    0.50
     Representation
    0.46
     Movement
    0.46
     بی
    0.45
     prophetic
    0.45
     speaker
    0.45
     A
    0.45
     그림
    0.43
     dashed
    0.43
    Activations Density 0.000%

    No Known Activations