© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2863
    Prev
    Next
    INDEX
    Explanations

    mathematical scripts

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

    creative text formats: letters

    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
     replacing
    0.42
     simile
    0.41
     CDMA
    0.39
     evaporating
    0.38
    <sub>
    0.38
    萜
    0.38
     あれ
    0.38
     accommodated
    0.37
    +...+
    0.37
     lecithin
    0.37
    POSITIVE LOGITS
    mathcal
    0.93
    mathfrak
    0.65
    ensuremath
    0.63
    mathbb
    0.62
    mathsf
    0.61
    mathscr
    0.59
    mathbf
    0.56
     mathvariant
    0.55
    CAL
    0.54
    cal
    0.53
    Activations Density 0.001%

    No Known Activations