© 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. 31-GEMMASCOPE-2-RES-262K
    7. 137726
    Prev
    Next
    INDEX
    Explanations

    performance, data, and tasks

    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
     τέ
    0.44
    ac
    0.44
    ag
    0.42
     până
    0.42
    ۲
    0.41
     все
    0.41
     ил
    0.40
    განიზ
    0.39
     incapac
    0.39
    agi
    0.39
    POSITIVE LOGITS
     colaborador
    0.42
    畤
    0.41
     ROOT
    0.40
     Roots
    0.39
    梅里
    0.39
    फै
    0.39
    潾
    0.39
     TA
    0.38
    Roots
    0.38
     localidad
    0.38
    Activations Density 0.005%

    No Known Activations