© 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. 1980
    Prev
    Next
    INDEX
    Explanations

    quality and performance indicators

    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
    낡
    0.41
    怵
    0.41
     hurriedly
    0.41
     chiede
    0.40
     badly
    0.39
    很不
    0.39
    有一些
    0.39
    奇怪
    0.39
    😖
    0.39
     horribly
    0.38
    POSITIVE LOGITS
     minimal
    1.63
     excellent
    1.52
    minimal
    1.44
     минима
    1.38
     optimal
    1.37
    excellent
    1.34
     flexibility
    1.34
     optimum
    1.33
     maximal
    1.31
     superior
    1.30
    Activations Density 0.583%

    No Known Activations