© 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. 40-GEMMASCOPE-2-RES-65K
    7. 797
    Prev
    Next
    INDEX
    Explanations

    Angular framework and typescript

    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_40_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
    pygame
    0.50
     pyruvate
    0.45
    Caucasian
    0.45
    缪
    0.43
    韌
    0.43
    MaxIntensity
    0.42
    glEnd
    0.42
    㯎
    0.41
    ‪‬
    0.41
    mRNA
    0.40
    POSITIVE LOGITS
     Angular
    1.85
    Angular
    1.60
     angular
    1.53
     Ng
    1.43
     ng
    1.41
    angular
    1.38
     ngOnInit
    1.29
    Ng
    1.24
    ngrx
    1.19
     NG
    1.18
    Activations Density 0.070%

    No Known Activations