© 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. 133091
    Prev
    Next
    INDEX
    Explanations

    demanded rights

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

    controlled environment, essentials, research

    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
    سات
    0.55
    esen
    0.50
    серед
    0.50
    жі
    0.49
    اق
    0.48
    zada
    0.48
     magistrate
    0.47
    <unused411>
    0.46
     vastu
    0.44
    akuan
    0.44
    POSITIVE LOGITS
    引用
    0.51
     стадии
    0.50
     Официа
    0.50
    <strong>
    0.45
     н
    0.44
     в
    0.43
     официа
    0.43
     што
    0.43
     utilice
    0.42
     outfield
    0.42
    Activations Density 0.000%

    No Known Activations