© 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. 102370
    Prev
    Next
    INDEX
    Explanations

    the best

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

    arm circles

    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
    ;\
    0.50
    ahati
    0.46
    xiv
    0.45
    eosin
    0.45
    ,\\
    0.44
    ेशनल
    0.44
    omegranate
    0.43
    emoji
    0.43
    ine
    0.43
    ঁচু
    0.43
    POSITIVE LOGITS
     goodwill
    0.44
     also
    0.42
     Goodwill
    0.42
     vuonna
    0.42
     lej
    0.42
    峙
    0.42
    нические
    0.41
    承担
    0.40
    孳
    0.40
     payable
    0.39
    Activations Density 0.001%

    No Known Activations