© 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. 202121
    Prev
    Next
    INDEX
    Explanations

    phrases like 'pursuant to' or 'or' followed by specific words

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

    measures, calculates, reset, challenges

    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
    ick
    0.56
    osa
    0.48
    ien
    0.47
    </i>
    0.47
     who
    0.46
    </h3>
    0.46
    ién
    0.45
     ver
    0.45
    om
    0.45
    qui
    0.45
    POSITIVE LOGITS
    Arkadaşlar
    0.53
    キッズ
    0.53
    飫
    0.53
    ेडियम
    0.49
    瞽
    0.49
    १०
    0.49
    것도
    0.48
    దేశ
    0.48
    province
    0.48
     Abub
    0.48
    Activations Density 0.001%

    No Known Activations