© 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. 30818
    Prev
    Next
    INDEX
    Explanations

    frankly, followed by punctuation

    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
    ির
    1.50
    í
    1.38
    يان
    1.34
     punches
    1.30
     Theorems
    1.30
    ა
    1.28
    ю
    1.27
    ра
    1.24
     couches
    1.24
     conspiracies
    1.23
    POSITIVE LOGITS
    ‌ی
    1.42
    ASTIC
    1.34
    )
    1.30
    FICATION
    1.16
     такі
    1.11
    ).
    1.09
    ‌ترین
    1.08
    nment
    1.07
    ž
    1.07
    C
    1.06
    Activations Density 0.001%

    No Known Activations