© 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. 251766
    Prev
    Next
    INDEX
    Explanations

    takes place or in half

    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
    Gosudarstvennyj
    0.15
     bactéries
    0.14
    Despatx
    0.13
    Pyrazole
    0.13
     sécrétion
    0.13
     prostagland
    0.13
     criaturas
    0.13
    髡
    0.12
    Imidazole
    0.12
    Methylsulfanyl
    0.12
    POSITIVE LOGITS
     and
    0.18
    and
    0.17
    ↵
    0.17
     I
    0.16
     &
    0.16
    -
    0.15
    s
    0.15
     ,
    0.15
    0
    0.15
     .
    0.15
    Activations Density 0.001%

    No Known Activations