© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156218
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation followed by words

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

    workplace assessments and processes

    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
     bege
    0.51
    FORMAN
    0.51
    Coef
    0.47
     terapi
    0.46
     baja
    0.46
    
    0.45
    ;
    0.45
     Bege
    0.44
     مف
    0.43
     pă
    0.43
    POSITIVE LOGITS
    ພວກເຮົາ
    0.52
    ક્સ
    0.48
    υτό
    0.47
     shortlisted
    0.46
     actes
    0.46
    У
    0.45
    ණ්ඩ
    0.45
     écologique
    0.45
    સી
    0.45
    скус
    0.45
    Activations Density 0.001%

    No Known Activations