© 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. 5680
    Prev
    Next
    INDEX
    Explanations

    made, deterioration, decided, starts

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

    misspellings and unusual spellings

    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
    ––
    0.58
    Bună
    0.58
    <unused2152>
    0.55
    .³
    0.54
    …?
    0.53
    ⁶
    0.51
    .…
    0.50
    <unused2123>
    0.50
    <unused2197>
    0.50
    ürnberg
    0.50
    POSITIVE LOGITS
     o
    0.82
     thei
    0.80
     th
    0.79
     thc
    0.79
     tha
    0.78
     lhe
    0.76
     о
    0.73
     u
    0.73
     wi
    0.71
     oth
    0.71
    Activations Density 0.084%

    No Known Activations