© 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. 4826
    Prev
    Next
    INDEX
    Explanations

    approximates or estimates

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

    obabooga

    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
     Almeida
    0.38
     შემ
    0.37
    }{|\
    0.37
    āda
    0.37
     Do
    0.36
    sche
    0.36
     ብዙውን
    0.36
     рам
    0.35
     subs
    0.35
     Sche
    0.35
    POSITIVE LOGITS
     approxim
    0.55
     ≈
    0.53
     approximates
    0.50
    ?=
    0.47
     aproxim
    0.46
    ≈
    0.44
     approximate
    0.44
     pribli
    0.43
     aprox
    0.43
     approximating
    0.42
    Activations Density 0.000%

    No Known Activations