© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47830
    Prev
    Next
    INDEX
    Explanations

    programming code and game characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sintomas
    0.51
    <unused79>
    0.50
    FindingsResponse
    0.50
    ampaikan
    0.47
     pharmacokinetic
    0.47
    ParamNum
    0.47
     रोजिक
    0.46
    рки
    0.45
    retto
    0.45
    rzez
    0.45
    POSITIVE LOGITS
    지와
    0.43
     и
    0.43
    私が
    0.40
     afford
    0.40
     historically
    0.40
     Hein
    0.40
     Monterey
    0.40
     Capacitor
    0.39
     Better
    0.39
     વિસ્તાર
    0.38
    Activations Density 0.001%

    No Known Activations