© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1715
    Prev
    Next
    INDEX
    Explanations

    options, characteristics, and roles

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

    instructions, descriptions, comments

    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
    --"
    0.54
     paltry
    0.53
     gleaned
    0.52
    --“
    0.51
     appreciably
    0.50
     ostensibly
    0.50
    "--
    0.49
     allowable
    0.49
    —-
    0.48
    --
    0.48
    POSITIVE LOGITS
     trough
    1.06
     ressources
    1.03
     advices
    0.98
     exercice
    0.94
     lenght
    0.91
     wich
    0.88
     hehe
    0.87
     ehm
    0.87
     nowadays
    0.86
     appart
    0.85
    Activations Density 0.805%

    No Known Activations