© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135972
    Prev
    Next
    INDEX
    Explanations

    limited email/phone access or next steps

    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
    potential
    0.53
    汾
    0.51
    likely
    0.48
    stability
    0.46
    probable
    0.46
    Ñ
    0.45
     قلب
    0.44
    轂
    0.43
    apk
    0.43
     घातक
    0.43
    POSITIVE LOGITS
     loi
    0.52
     caracteres
    0.50
     Londra
    0.47
     foi
    0.47
     ustal
    0.46
     leurs
    0.46
     nere
    0.45
     fue
    0.45
     segera
    0.45
     Anonymous
    0.45
    Activations Density 0.006%

    No Known Activations