© 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. 48146
    Prev
    Next
    INDEX
    Explanations

    structure related to: [ ] or *

    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
     doubles
    0.49
     outbound
    0.48
     decou
    0.47
    ضي
    0.47
    жом
    0.46
     coach
    0.46
     cran
    0.45
    測
    0.44
     الرس
    0.44
     isset
    0.44
    POSITIVE LOGITS
    }\,
    0.48
    л
    0.47
    of
    0.46
    }=
    0.45
     हजार
    0.45
    }/
    0.43
    こ
    0.42
    ८
    0.42
    厚生
    0.42
    ठ
    0.42
    Activations Density 0.001%

    No Known Activations