© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 45023
    Prev
    Next
    INDEX
    Explanations

    TAP briefing

    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
    ﻕ
    0.44
    ុន
    0.42
    ş
    0.41
     Orr
    0.39
    ర్
    0.39
    জ
    0.39
    力
    0.37
     gigs
    0.37
    ্টে
    0.37
    𝒕
    0.37
    POSITIVE LOGITS
     wasnt
    0.56
     youre
    0.55
     isnt
    0.55
     doesnt
    0.52
    mdash
    0.52
    ००
    0.51
     theyre
    0.51
     couldnt
    0.51
     arent
    0.49
     nbsp
    0.48
    Activations Density 0.021%

    No Known Activations