© 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-65K
    7. 31096
    Prev
    Next
    INDEX
    Explanations

    ai.google.dev or meta.com links

    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
    ீர்க
    0.44
     அழ
    0.42
    য়ং
    0.41
     ά
    0.40
     ቦታ
    0.40
     செய
    0.40
     ஏனெனில்
    0.39
    埬
    0.39
     deceit
    0.38
     תק
    0.38
    POSITIVE LOGITS
     vergangenen
    0.41
    ʽ
    0.38
     nominated
    0.37
    via
    0.36
    upol
    0.36
     чемпион
    0.36
    spolit
    0.36
    wikipedia
    0.35
     politik
    0.35
    riele
    0.35
    Activations Density 0.041%

    No Known Activations