© 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. 192388
    Prev
    Next
    INDEX
    Explanations

    next sequence

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

    biological structure and function

    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
    Negative Logits
     CONTRIBUT
    0.44
    তম
    0.43
     Membership
    0.43
     workplace
    0.42
    :',
    0.42
     pending
    0.42
     innermost
    0.42
     Initiation
    0.41
    :",
    0.41
     fiind
    0.41
    POSITIVE LOGITS
     chicas
    0.53
    zonego
    0.49
    Sac
    0.48
    ровали
    0.47
     padassa
    0.47
    া
    0.46
    quets
    0.46
    Agregar
    0.46
    ोब
    0.46
     Fools
    0.45
    Activations Density 0.000%

    No Known Activations