© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21360
    Prev
    Next
    INDEX
    Explanations

    git branches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    varage
    0.44
    İstanbul
    0.43
    ଲ
    0.42
    gaver
    0.41
     απα
    0.40
    possible
    0.40
    шения
    0.39
    yards
    0.39
    ပါတယ်။
    0.38
    㳑
    0.38
    POSITIVE LOGITS
     Grammar
    0.47
     "
    0.43
     positi
    0.43
     IMP
    0.43
     dedic
    0.43
     rufis
    0.43
     clave
    0.42
    тику
    0.42
     Dau
    0.42
     Slave
    0.42
    Activations Density 0.004%

    No Known Activations