© 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. 170326
    Prev
    Next
    INDEX
    Explanations

    legal monetary contexts

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

    vendor evaluation and services

    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
    ే
    0.51
    ходи
    0.45
    kub
    0.42
    وسع
    0.42
     vitesse
    0.41
    corper
    0.41
    രാ
    0.40
    東
    0.40
    こうした
    0.40
    boden
    0.40
    POSITIVE LOGITS
     coworking
    0.60
     copyspace
    0.59
     mosaic
    0.58
     demonstr
    0.56
     catalogs
    0.56
     tet
    0.55
     ciphertext
    0.54
     monument
    0.53
     cryptocurrency
    0.52
     caseload
    0.52
    Activations Density 0.000%

    No Known Activations