© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203827
    Prev
    Next
    INDEX
    Explanations

    Etsy or essentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    0.55
    anud
    0.44
    ({\
    0.43
     functionalities
    0.42
    ებას
    0.42
     entity
    0.42
    ,
    0.42
    erà
    0.42
    /
    0.41
     entities
    0.40
    POSITIVE LOGITS
     reaksi
    0.49
     lão
    0.49
     જૂ
    0.49
     tedes
    0.48
     khat
    0.48
     பழைய
    0.48
     tedesco
    0.48
    ﻋ
    0.47
     lesiones
    0.46
     umur
    0.46
    Activations Density 0.001%

    No Known Activations