© 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-65K
    7. 4527
    Prev
    Next
    INDEX
    Explanations

    colors and descriptions

    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_65k_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
     aix
    0.44
    <start_of_image>
    0.42
    l
    0.40
    یک
    0.39
     ein
    0.39
     oz
    0.38
    s
    0.37
    الص
    0.37
    C
    0.37
     ose
    0.37
    POSITIVE LOGITS
     tinge
    0.47
     supremacist
    0.42
     rulemaking
    0.40
     convoy
    0.40
     jeopardize
    0.39
     labelling
    0.39
     हितों
    0.38
    绩效
    0.38
    atletas
    0.38
     participatory
    0.37
    Activations Density 0.087%

    No Known Activations