© 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. 64807
    Prev
    Next
    INDEX
    Explanations

    dial variations

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

    language diversity and specific conditions

    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
     mandated
    0.54
     mobilization
    0.50
    ↵
    0.49
     arguably
    0.48
     accounted
    0.48
    D
    0.47
    েন্ড
    0.46
     equestrian
    0.46
     traff
    0.46
     maximizes
    0.46
    POSITIVE LOGITS
    郗
    0.44
    惊喜
    0.44
    喜び
    0.44
     июле
    0.43
    态度
    0.43
    乐趣
    0.43
    狰
    0.43
     علیہ
    0.42
    带领
    0.42
    蛩
    0.42
    Activations Density 0.000%

    No Known Activations