© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1158
    Prev
    Next
    INDEX
    Explanations

    Low, Medium, High

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lių
    0.54
    śmy
    0.50
    mpi
    0.49
    ỳ
    0.47
    agę
    0.46
    udarstvennyj
    0.46
    ácie
    0.46
    κό
    0.46
    casian
    0.45
     চে
    0.45
    POSITIVE LOGITS
    נ
    0.46
    AR
    0.46
     זה
    0.43
     canalicul
    0.43
     descriptors
    0.42
     angepasst
    0.41
    AS
    0.40
     ಸುಬ್ಬ
    0.40
    !
    0.40
    。
    0.39
    Activations Density 0.006%

    No Known Activations