© 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. 200319
    Prev
    Next
    INDEX
    Explanations

    conditional instructions and details

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

    Habit stacking, linking, creating

    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
    𝗮
    0.55
     하지
    0.52
    𝒂
    0.52
    塩
    0.52
     ポイント
    0.51
    cuterie
    0.49
     Vestone
    0.48
    口座
    0.48
    리지
    0.48
    パ
    0.48
    POSITIVE LOGITS
     eu
    0.46
     musia
    0.46
     Mori
    0.42
     gennem
    0.42
    颢
    0.41
     humanist
    0.41
    zieć
    0.41
     przez
    0.40
     splendor
    0.40
     foregoing
    0.40
    Activations Density 0.000%

    No Known Activations