© 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. 106105
    Prev
    Next
    INDEX
    Explanations

    editing your movies

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

    simple shelf

    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
     ഉൾ
    0.46
     ഉള്‍
    0.46
    oltre
    0.46
     πολλά
    0.45
     πολλ
    0.45
    ⒏
    0.44
     ১৯৮
    0.44
    বর্তমানে
    0.43
     permanently
    0.42
    有不少
    0.41
    POSITIVE LOGITS
    另一方面
    0.44
     THEM
    0.40
     anorexia
    0.39
    مكن
    0.39
    愕
    0.39
     hemolysis
    0.38
    му
    0.38
     রহমানকে
    0.38
    模仿
    0.38
     оказалось
    0.37
    Activations Density 0.000%

    No Known Activations