© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43165
    Prev
    Next
    INDEX
    Explanations

    account needs, savings made, sign and send

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

    perspective or relative motion

    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
     ער
    0.46
    त्री
    0.45
    ১৪
    0.45
     treasurer
    0.45
    ETT
    0.44
    ਦ
    0.44
    隴
    0.44
    Jer
    0.43
    ረስ
    0.43
     leveling
    0.43
    POSITIVE LOGITS
    ų
    0.48
    ivă
    0.46
     transformação
    0.46
     după
    0.46
    ēi
    0.46
     kwamba
    0.45
     tessuto
    0.44
     নায়
    0.44
    vič
    0.43
    idać
    0.43
    Activations Density 0.001%

    No Known Activations