© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8570
    Prev
    Next
    INDEX
    Explanations

    Bosmer, Golang, Dolce, OGNL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ﺸ
    1.63
    ﺒ
    1.52
     chọn
    1.34
    ﺨ
    1.33
     juicy
    1.30
    assing
    1.27
    itching
    1.27
    いただけます
    1.25
    ART
    1.24
    awa
    1.22
    POSITIVE LOGITS
    ק
    1.93
    ك
    1.74
    ט
    1.67
    lardan
    1.59
    лари
    1.55
    홋
    1.55
    cases
    1.55
    齐全
    1.54
    라도
    1.51
    𝓊
    1.48
    Activations Density 0.457%

    No Known Activations