© 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. 1412
    Prev
    Next
    INDEX
    Explanations

    a.m

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

    about to / the following / a flexible

    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
     >>
    0.16
     p
    0.16
     :
    0.15
    p
    0.15
    n
    0.15
     ;
    0.15
     >>>
    0.15
    no
    0.15
     n
    0.15
     _
    0.15
    POSITIVE LOGITS
     sacraments
    0.14
     ecclesiastical
    0.14
     calibrations
    0.14
    ლების
    0.13
     coalitions
    0.13
     ligands
    0.13
     sacram
    0.13
     ornamentation
    0.13
     husbandry
    0.12
    體的
    0.12
    Activations Density 0.000%

    No Known Activations