© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60064
    Prev
    Next
    INDEX
    Explanations

    Job guaranteed

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

    about simple or personal

    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
    čar
    0.45
    ப்படாத
    0.42
    误
    0.41
    eln
    0.40
     Unavailable
    0.39
    相
    0.39
    佐
    0.39
    小于
    0.39
    šić
    0.39
    曙
    0.38
    POSITIVE LOGITS
    APPROVAL
    0.54
     côt
    0.47
     agglut
    0.46
     compres
    0.45
    OLOG
    0.45
    Businessman
    0.45
     MACHIN
    0.45
    expenses
    0.45
    IR
    0.44
     okolic
    0.44
    Activations Density 0.000%

    No Known Activations