© 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. 185285
    Prev
    Next
    INDEX
    Explanations

    have been applied

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

    finding and determining conditions

    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
     zentral
    0.49
     faktor
    0.45
     architekt
    0.45
    깥
    0.45
     direktor
    0.44
     natürliche
    0.44
     Schlag
    0.44
    ೃಷ್ಣ
    0.44
    VHS
    0.43
    ణాలు
    0.42
    POSITIVE LOGITS
    ===
    0.51
     Nox
    0.47
     Concept
    0.45
     মজ
    0.44
     удоволь
    0.44
    branded
    0.44
    मर
    0.43
    StructOf
    0.43
     गावा
    0.42
    Parad
    0.42
    Activations Density 0.000%

    No Known Activations