© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213612
    Prev
    Next
    INDEX
    Explanations

    Yandex services and products

    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
     seule
    0.38
     sozinha
    0.37
     scream
    0.36
     parted
    0.36
     ಥ
    0.35
     дохода
    0.35
     čist
    0.35
     нарко
    0.34
    깐
    0.34
     każdy
    0.34
    POSITIVE LOGITS
     Irina
    0.44
     meteorological
    0.42
    鳩
    0.41
    /-
    0.41
     Clouds
    0.40
     Schools
    0.39
     Meteorological
    0.39
    oblasts
    0.39
    matching
    0.39
    -+
    0.39
    Activations Density 0.000%

    No Known Activations