© 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. 76221
    Prev
    Next
    INDEX
    Explanations

    touch withdealing withno constraint

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

    need to immigrate

    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
    _{+}-
    0.48
    FlashValue
    0.48
     औद्योगिक
    0.47
    aklar
    0.47
     अंशु
    0.47
    ismarck
    0.46
    vori
    0.46
    Ắ
    0.46
    تميز
    0.45
    ätzung
    0.45
    POSITIVE LOGITS
     Object
    0.49
     Strategies
    0.48
     Aliens
    0.44
     Channel
    0.43
     commissioner
    0.42
     Code
    0.42
     Pipeline
    0.41
    ють
    0.41
     Nucleic
    0.41
     Stairs
    0.41
    Activations Density 0.001%

    No Known Activations