© 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-262K
    7. 11392
    Prev
    Next
    INDEX
    Explanations

    media types cannot

    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
     d
    0.41
     των
    0.40
    ing
    0.38
    ids
    0.37
    timed
    0.37
     όσο
    0.37
    я
    0.35
     delle
    0.34
    id
    0.34
     Pearson
    0.34
    POSITIVE LOGITS
    🐊
    0.43
     apoyar
    0.41
    후
    0.41
    ByDefault
    0.40
     intravenously
    0.40
     ㅋㅋ
    0.40
     susu
    0.39
    🚔
    0.39
    Categoria
    0.39
    Peq
    0.39
    Activations Density 0.001%

    No Known Activations