© 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. 187530
    Prev
    Next
    INDEX
    Explanations

    nonprofit organizations

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

    culture and combat differences

    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
     carattere
    0.46
     pís
    0.44
     Teen
    0.44
    r
    0.43
     supernatant
    0.43
     porcelain
    0.42
    راز
    0.42
    覀
    0.41
    NUCLEAR
    0.40
    n
    0.40
    POSITIVE LOGITS
    akah
    0.52
    Ish
    0.50
     ఇంకా
    0.50
    odeon
    0.48
    acho
    0.48
     Auburn
    0.48
     निजा
    0.47
     मुआव
    0.47
     Larkin
    0.47
     codewords
    0.46
    Activations Density 0.000%

    No Known Activations