© 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. 2280
    Prev
    Next
    INDEX
    Explanations

    they + verb

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

    classifications and domains

    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
    Shock
    0.44
    戶
    0.43
     է
    0.43
     CTCF
    0.42
    午後
    0.41
    qt
    0.40
     Huo
    0.38
    户
    0.38
    异
    0.38
    Collider
    0.38
    POSITIVE LOGITS
     weren
    0.58
     arrived
    0.49
     didn
    0.46
     couldn
    0.44
     wouldn
    0.43
     precipitate
    0.43
     feared
    0.42
     drank
    0.42
     don
    0.41
     raced
    0.41
    Activations Density 0.000%

    No Known Activations