© 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. 78253
    Prev
    Next
    INDEX
    Explanations

    includes both

    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
    ﻤ
    0.48
    いる
    0.46
    痺
    0.44
    ತಾ
    0.44
     skeptic
    0.43
    ﻪ
    0.42
    טי
    0.41
    蚪
    0.41
     могла
    0.41
     recruited
    0.40
    POSITIVE LOGITS
    c
    0.50
     hind
    0.49
    ن
    0.48
     fech
    0.48
    h
    0.46
     weiß
    0.46
     soot
    0.46
    شون
    0.46
     dorm
    0.45
     orange
    0.44
    Activations Density 0.001%

    No Known Activations