© 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. 2018
    Prev
    Next
    INDEX
    Explanations

    names after prepositions

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

    names following punctuation

    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
     Vestone
    0.33
     elution
    0.33
     $*$-
    0.33
     fdPar
    0.33
     optimale
    0.32
     locatie
    0.32
    
    0.31
     %``
    0.31
     inhibit
    0.31
     armazen
    0.31
    POSITIVE LOGITS
     Michael
    0.62
     Robert
    0.60
     John
    0.59
     George
    0.58
     Richard
    0.57
     Jonathan
    0.57
     Jimmy
    0.55
     Donald
    0.55
     Tony
    0.55
     Barack
    0.54
    Activations Density 0.835%

    No Known Activations