© 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. 4977
    Prev
    Next
    INDEX
    Explanations

    in followed by common phrases

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

    in multiple ways

    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
     appreciably
    0.66
     manifestly
    0.57
     nominally
    0.53
     broadly
    0.49
     markedly
    0.48
     putative
    0.47
     fanciful
    0.46
     :-
    0.45
     ostensibly
    0.45
     conspicuously
    0.44
    POSITIVE LOGITS
     regards
    0.71
     Regards
    0.57
    Correlation
    0.53
     correlation
    0.49
     rightfully
    0.49
     Correlation
    0.48
     referencia
    0.47
     result
    0.46
     fruition
    0.45
     resemblance
    0.44
    Activations Density 0.161%

    No Known Activations