© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14030
    Prev
    Next
    INDEX
    Explanations

    exam prep and answers

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

    exam discussions

    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_16k_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
     साय
    0.46
     —¿
    0.45
     लेखा
    0.42
    classteacher
    0.42
    我们就
    0.41
    找到了
    0.40
    酺
    0.40
    StateToProps
    0.40
     수가
    0.40
    Databaze
    0.40
    POSITIVE LOGITS
    &
    0.52
     PRIM
    0.45
     POR
    0.45
     P
    0.45
     PACKAGE
    0.44
     нажмите
    0.43
     Package
    0.43
     Visibility
    0.42
    </strong>
    0.41
     EAST
    0.41
    Activations Density 0.000%

    No Known Activations