© 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. 42998
    Prev
    Next
    INDEX
    Explanations

    crazy ideas and comparisons

    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
     예배
    0.58
    にっいて
    0.53
    ヶ
    0.48
    ☦
    0.48
    Parrocchia
    0.48
    ጳ
    0.48
    <unused56>
    0.47
    ани
    0.46
    ੴ
    0.46
    resultlist
    0.46
    POSITIVE LOGITS
     like
    0.61
     craz
    0.55
     Crazy
    0.54
    ↵
    0.53
     manually
    0.53
     z
    0.52
     Z
    0.52
     think
    0.51
     crazy
    0.51
     Moon
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.