© 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. 131338
    Prev
    Next
    INDEX
    Explanations

    military coup, broken leg, email boxes, wicker basket

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

    historical contexts and data formats

    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
    ↵
    0.31
    1
    0.31
     this
    0.31
    5
    0.31
     the
    0.30
    .
    0.30
     each
    0.30
    :
    0.29
     these
    0.28
    。
    0.28
    POSITIVE LOGITS
     monstru
    0.34
     मायणी
    0.34
    Ნ
    0.32
     шпански
    0.31
     logotipo
    0.30
     melanch
    0.30
     standart
    0.30
    ៣
    0.30
     cowardly
    0.30
    賈
    0.30
    Activations Density 0.000%

    No Known Activations