© 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. 142812
    Prev
    Next
    INDEX
    Explanations

    right to, how to, for visitors, need for, can be

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

    coordinate basis vectors

    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
    itt
    0.52
    ங்கிணை
    0.50
    ipp
    0.46
    intégr
    0.46
    ulosa
    0.46
    olom
    0.44
    ř
    0.44
     Drinking
    0.44
    oradi
    0.44
    uj
    0.43
    POSITIVE LOGITS
    
    0.53
     gamepad
    0.50
     niemand
    0.49
    NERVE
    0.48
    Ｓ
    0.48
    NG
    0.47
    ERTY
    0.46
     chưa
    0.46
    IDENTAL
    0.45
    IENTE
    0.45
    Activations Density 0.000%

    No Known Activations