© 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. 228172
    Prev
    Next
    INDEX
    Explanations

    provide information and freebies

    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
    }))
    0.52
    ,}
    0.43
    ,/
    0.41
    )、
    0.41
    Axes
    0.41
     webbing
    0.40
    )^
    0.40
    AGA
    0.40
     fixed
    0.39
    ,’
    0.39
    POSITIVE LOGITS
    körper
    0.48
    ྨ
    0.44
    奏
    0.44
    spanning
    0.42
    facing
    0.42
     homenagem
    0.41
    cient
    0.41
    面向
    0.41
    chränk
    0.41
     beachten
    0.41
    Activations Density 0.003%

    No Known Activations