© 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. 46675
    Prev
    Next
    INDEX
    Explanations

    common words

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

    danger and risks

    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
    icians
    0.38
    …
    0.37
     জন্য
    0.36
     despite
    0.35
    guessed
    0.35
     bunda
    0.35
    <i>
    0.35
    prompt
    0.35
     malgré
    0.35
    ніка
    0.35
    POSITIVE LOGITS
    ૩
    0.46
     नैसर्गिक
    0.42
     删除
    0.41
    葢
    0.41
     रोकने
    0.41
    を除く
    0.40
    রীণ
    0.40
    栘
    0.40
     scrollBody
    0.39
     ebenso
    0.39
    Activations Density 0.000%

    No Known Activations