© 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. 40-GEMMASCOPE-2-RES-262K
    7. 136725
    Prev
    Next
    INDEX
    Explanations

    download, contains, dinner

    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_40_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
    𝐜
    0.39
     negligible
    0.39
    緎
    0.38
     loafers
    0.38
     tolerant
    0.38
     spongy
    0.38
     neurop
    0.37
    聵
    0.37
     sprouting
    0.37
     caes
    0.37
    POSITIVE LOGITS
    poster
    0.46
    éditeur
    0.41
     звук
    0.41
    member
    0.41
     വിൽപ്പന
    0.41
     प्रीत
    0.40
    મે
    0.40
    role
    0.39
    unun
    0.39
    MNOP
    0.39
    Activations Density 0.000%

    No Known Activations