© 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. 2209
    Prev
    Next
    INDEX
    Explanations

    pronoun or noun followed by verb

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

    impressionistic paintings, streamed, evaporated, shreds

    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
     seperate
    0.57
     seper
    0.54
     extremamente
    0.52
     extremely
    0.52
    非常的
    0.52
     completely
    0.51
     Completely
    0.50
    <unused2130>
    0.50
     decreases
    0.50
     повністю
    0.49
    POSITIVE LOGITS
     esche
    0.94
     dutiful
    0.92
     deftly
    0.92
    倘
    0.82
     sundry
    0.82
     doubtless
    0.81
     proffered
    0.80
     merr
    0.79
     cheerfully
    0.78
     plump
    0.76
    Activations Density 0.753%

    No Known Activations