© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17491
    Prev
    Next
    INDEX
    Explanations

    image hosting services

    np_acts-logits-general · gemini-2.5-flash-lite

    downshiftology recipes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    穗
    0.42
    コーチ
    0.38
    ostí
    0.38
     পোকামাকড়
    0.37
    وج
    0.36
     سپور
    0.36
    隨著
    0.35
    ဌ
    0.35
     моло
    0.35
    gov
    0.35
    POSITIVE LOGITS
     alb
    0.64
    Alb
    0.59
     ALB
    0.59
     Alb
    0.58
     Albany
    0.53
    albums
    0.47
     Albums
    0.46
    alb
    0.46
     SB
    0.45
     albums
    0.45
    Activations Density 0.000%

    No Known Activations