© 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. 107471
    Prev
    Next
    INDEX
    Explanations

    last 10 years

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

    Active Directory

    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
    ের
    0.53
     únicas
    0.52
     ставак
    0.51
     offerte
    0.47
     investasi
    0.47
     μο
    0.46
     wikipagina
    0.46
    🤔
    0.46
     lấy
    0.46
     ofertas
    0.46
    POSITIVE LOGITS
     noct
    0.50
     undes
    0.44
     Stopwatch
    0.41
    沈
    0.40
     उतनी
    0.39
     Cooper
    0.38
     Webster
    0.38
     espectadores
    0.38
     Visible
    0.38
     Publikum
    0.37
    Activations Density 0.000%

    No Known Activations