© 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-262K
    7. 34837
    Prev
    Next
    INDEX
    Explanations

    past events and states

    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_262k_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
     ankaŭ
    0.47
    çok
    0.46
    bootstrap
    0.46
    api
    0.45
    base
    0.44
    ç
    0.43
    ık
    0.42
    ᠢ
    0.41
    id
    0.41
    시고
    0.40
    POSITIVE LOGITS
     kemarin
    0.44
    дження
    0.41
     あれ
    0.40
    ****",
    0.40
     اسمها
    0.40
     abnormality
    0.39
     ieri
    0.38
     yesterday
    0.38
     normes
    0.38
     wèi
    0.38
    Activations Density 0.005%

    No Known Activations