© 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. 199803
    Prev
    Next
    INDEX
    Explanations

    niche mount hunter damage body

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

    to get

    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
    ет
    0.47
    支
    0.46
    足以
    0.46
    往
    0.46
    ớm
    0.45
    вших
    0.44
    的学习
    0.43
    ହା
    0.43
    ир
    0.43
    的
    0.43
    POSITIVE LOGITS
     pula
    0.46
     aficionados
    0.45
     volunt
    0.44
     passengers
    0.44
     intensiv
    0.44
     Pilih
    0.44
     intens
    0.43
     allerg
    0.42
     کاربران
    0.42
     Alvar
    0.42
    Activations Density 0.001%

    No Known Activations