© 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. 165542
    Prev
    Next
    INDEX
    Explanations

    apron design or fast shifts

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

    dungeon master

    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
    فري
    0.52
    Frequency
    0.49
    φα
    0.46
    τον
    0.46
     <!--<
    0.45
    novu
    0.45
     náz
    0.44
    న్ని
    0.43
    тельным
    0.43
    Veh
    0.43
    POSITIVE LOGITS
     theatrical
    0.50
    glucose
    0.43
    ۔
    0.41
     exploitation
    0.41
     rate
    0.41
     apple
    0.41
     RUD
    0.40
    ńska
    0.40
     RATE
    0.40
    。
    0.40
    Activations Density 0.001%

    No Known Activations