© 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. 177
    Prev
    Next
    INDEX
    Explanations

    approving or following 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
     Comissão
    0.27
    𝐄
    0.27
    㐄
    0.27
     fleste
    0.26
    𝔰
    0.26
     ক্ষেত্রেই
    0.25
     différente
    0.25
    ⏸
    0.25
     ו
    0.24
     그리고
    0.24
    POSITIVE LOGITS
    el
    0.49
    i
    0.49
    k
    0.48
    er
    0.47
    ar
    0.46
    ي
    0.45
    a
    0.45
    1
    0.44
    2
    0.43
    an
    0.43
    Activations Density 0.041%

    No Known Activations