© 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. 239534
    Prev
    Next
    INDEX
    Explanations

    future enablement

    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
    essero
    0.52
     бывают
    0.49
    ถึง
    0.47
    婁
    0.46
     бывает
    0.46
     ہوتا
    0.45
    蘇
    0.44
    끔
    0.44
    acchati
    0.44
    承認
    0.43
    POSITIVE LOGITS
     landlords
    0.46
     majest
    0.46
    -
    0.45
     fireplaces
    0.44
     rain
    0.44
     circled
    0.44
     jungle
    0.43
    ，
    0.43
     ring
    0.43
     circle
    0.43
    Activations Density 0.000%

    No Known Activations