© 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. 112684
    Prev
    Next
    INDEX
    Explanations

    tickets to

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

    concepts related to dynamics, value, focus

    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
     illusions
    0.46
    ULAR
    0.45
    搵
    0.45
    FirstFit
    0.45
     циф
    0.43
     raro
    0.42
    achievement
    0.42
    ↵↵
    0.42
     coherent
    0.42
     enviable
    0.41
    POSITIVE LOGITS
    rsi
    0.48
    ড়ের
    0.44
     Quando
    0.43
     Frazier
    0.43
    ɓ
    0.42
    otte
    0.41
     När
    0.41
     Squirrel
    0.41
     Moto
    0.41
    aconda
    0.41
    Activations Density 0.000%

    No Known Activations