© 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. 151586
    Prev
    Next
    INDEX
    Explanations

    allowed / prohibited / shall

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

    French or false implications

    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
    enqueue
    0.49
     않았
    0.47
    繧
    0.46
    γων
    0.45
    睃
    0.44
     jButton
    0.44
    視覺
    0.43
    看護
    0.43
    قافة
    0.43
    inguistic
    0.43
    POSITIVE LOGITS
     Moż
    0.50
     pomiędzy
    0.46
     Fern
    0.46
     সবসময়
    0.45
     R
    0.43
     Tanto
    0.43
     ranc
    0.43
     (~
    0.42
     fern
    0.42
     between
    0.41
    Activations Density 0.001%

    No Known Activations