© 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. 142125
    Prev
    Next
    INDEX
    Explanations

    He was, good tea, phase focused, five stars, Stark laws

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

    closed-source vs open-weights

    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
    ó
    0.55
     एजु
    0.54
     जॉ
    0.54
    ä
    0.52
     dà
    0.50
     rå
    0.48
     Encourage
    0.48
    á
    0.48
     BE
    0.47
    òn
    0.47
    POSITIVE LOGITS
    Versioning
    0.47
    設定
    0.43
    와이스
    0.42
    姩
    0.42
    "-"
    0.42
    感が
    0.41
    မဲ့
    0.41
     Saka
    0.41
    ついて
    0.41
    getBounding
    0.40
    Activations Density 0.000%

    No Known Activations