© 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. 7600
    Prev
    Next
    INDEX
    Explanations

    points, spacing, leading, millimeters, bps

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

    tiny units and spacing

    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
     welkom
    0.41
     Imani
    0.41
     Sle
    0.40
    跤
    0.38
     mưa
    0.38
     velho
    0.38
     Schae
    0.37
    賄
    0.37
     rot
    0.37
    ક્ત
    0.37
    POSITIVE LOGITS
    thickmathspace
    0.68
    smallskip
    0.64
    spacing
    0.59
    millimeters
    0.59
     millimeters
    0.59
     mm
    0.58
    medskip
    0.57
     millimeter
    0.55
    bigskip
    0.55
    mspace
    0.55
    Activations Density 0.005%

    No Known Activations