© 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. 46118
    Prev
    Next
    INDEX
    Explanations

    rear speakers

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

    // J pattern

    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
    h
    0.48
    вим
    0.46
    hv
    0.46
    openid
    0.45
    hyp
    0.43
     considere
    0.43
     предпочита
    0.42
    ’.
    0.41
    arters
    0.41
    時期
    0.41
    POSITIVE LOGITS
     爱
    0.50
    味道
    0.49
     电
    0.48
    老板
    0.48
     ἔ
    0.48
     TEACH
    0.48
     irgendwo
    0.48
     হস্তে
    0.47
     巴
    0.47
     pręd
    0.46
    Activations Density 0.000%

    No Known Activations