© 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. 174045
    Prev
    Next
    INDEX
    Explanations

    phone numbers and contact information

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

    sentinel against, tailor, vulnerability, local currencies

    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
     F
    0.52
    ’;
    0.47
     humble
    0.47
    etto
    0.46
    ociation
    0.46
    andelier
    0.46
     journée
    0.46
     îng
    0.46
     slows
    0.45
     الف
    0.45
    POSITIVE LOGITS
    𝕡
    0.53
     세포
    0.51
    یف
    0.48
     Hfn
    0.46
    𝜌
    0.46
    댈
    0.46
    치
    0.46
    ר
    0.45
    ل
    0.45
    Раз
    0.44
    Activations Density 0.001%

    No Known Activations