© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2902
    Prev
    Next
    INDEX
    Explanations

    github, Hugging Face, LMSYS Org

    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
     prescriptive
    0.40
    톄
    0.39
     diminution
    0.37
     جمل
    0.37
     avoidance
    0.36
    айл
    0.36
     operative
    0.36
     deliberations
    0.36
     passages
    0.35
     interruption
    0.35
    POSITIVE LOGITS
     Patreon
    0.53
    团队
    0.49
     (@
    0.48
     以及
    0.47
    github
    0.43
     prolific
    0.43
    _
    0.43
    ơm
    0.42
     Github
    0.42
    出品
    0.42
    Activations Density 0.057%

    No Known Activations