© 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. 59693
    Prev
    Next
    INDEX
    Explanations

    years 2008

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

    empirical description

    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
     A
    0.46
     Kevin
    0.45
    িয়া
    0.44
     C
    0.43
    ăng
    0.41
     Solutions
    0.41
     Ltd
    0.41
     Springfield
    0.41
     Wouldn
    0.40
     trying
    0.39
    POSITIVE LOGITS
     fundament
    0.52
     empirical
    0.46
     empir
    0.43
    empirical
    0.41
     citer
    0.41
     scru
    0.41
     empirically
    0.40
     derivable
    0.39
    畴
    0.39
    udem
    0.39
    Activations Density 0.001%

    No Known Activations