© 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. 111076
    Prev
    Next
    INDEX
    Explanations

    High School

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

    recommendations; suggestions

    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
    𒅀
    0.49
    久し
    0.46
    Portada
    0.44
    ]}/${
    0.44
    🦞
    0.43
    клю
    0.43
    NaClO
    0.42
    proble
    0.41
    ҕ
    0.41
    az
    0.41
    POSITIVE LOGITS
    を受けて
    0.48
     رفتار
    0.44
    人为
    0.43
     Think
    0.43
     warped
    0.41
     nerveux
    0.41
     Steering
    0.41
     Levi
    0.41
     coerced
    0.41
     neurotic
    0.40
    Activations Density 0.002%

    No Known Activations