© 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. 90973
    Prev
    Next
    INDEX
    Explanations

    versions and later

    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
     contour
    0.42
     toughest
    0.40
    耐
    0.40
    ahami
    0.40
     contours
    0.40
     trimmer
    0.40
     siento
    0.39
    是很
    0.39
     somewhat
    0.38
     footprint
    0.38
    POSITIVE LOGITS
    Organizer
    0.44
     onwards
    0.42
    悆
    0.42
    BA
    0.41
    rators
    0.41
    щаются
    0.41
    少なくとも
    0.41
    LAM
    0.40
    llabus
    0.40
    NAS
    0.39
    Activations Density 0.002%

    No Known Activations