© 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. 200068
    Prev
    Next
    INDEX
    Explanations

    Editing professionals

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

    handling specific items or situations

    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
    感動
    0.54
    恋愛
    0.54
    ઊ
    0.53
    MessageNow
    0.52
    Mannschaft
    0.52
    સિંહ
    0.52
    এশিয়া
    0.51
    勝ち
    0.51
    屒
    0.50
    権
    0.50
    POSITIVE LOGITS
     sophistic
    0.48
     whats
    0.47
     namesake
    0.46
     entire
    0.46
     asking
    0.46
     Skies
    0.46
     ingredient
    0.45
     said
    0.44
     Extended
    0.44
     sofistic
    0.44
    Activations Density 0.000%

    No Known Activations