© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13426
    Prev
    Next
    INDEX
    Explanations

    has been since

    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
    ดา
    0.55
    ر
    0.51
    রো
    0.49
     größ
    0.48
    畛
    0.48
    র
    0.46
    ب
    0.46
    склю
    0.46
    스타
    0.46
     poudre
    0.46
    POSITIVE LOGITS
     compared
    0.47
    compared
    0.44
    times
    0.43
     modeling
    0.41
     laboral
    0.41
     separated
    0.41
     modelling
    0.41
     systems
    0.40
     اداره
    0.40
    ′
    0.40
    Activations Density 0.002%

    No Known Activations