© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 184546
    Prev
    Next
    INDEX
    Explanations

    phrases after periods

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

    excessively, local, frat, line

    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
    א
    0.50
    }[[
    0.47
    
    0.46
    았
    0.46
     ricev
    0.45
     Gage
    0.44
    
    0.43
    ע
    0.43
     Incidentally
    0.43
    _*
    0.42
    POSITIVE LOGITS
     expériences
    0.53
    ormais
    0.52
    KU
    0.49
     alumnos
    0.48
     Beruf
    0.48
    zeptember
    0.47
    prisoners
    0.47
    portfolio
    0.46
    ,
    0.46
     profesores
    0.46
    Activations Density 0.000%

    No Known Activations