© 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. 44873
    Prev
    Next
    INDEX
    Explanations

    questions about actions or definitions

    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
    2
    1.70
    1
    1.55
    te
    1.48
    )
    1.43
    >
    1.38
    7
    1.37
    5
    1.36
    4
    1.36
    3
    1.33
    8
    1.32
    POSITIVE LOGITS
    یل
    1.20
    ضافة
    1.20
    是你
    1.19
    ುದು
    1.18
    𝐢
    1.16
    硋
    1.16
    య
    1.15
    یی
    1.13
    idł
    1.13
    حسن
    1.11
    Activations Density 0.000%

    No Known Activations