© 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. 45011
    Prev
    Next
    INDEX
    Explanations

    Silicon, cracking

    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
    簀
    1.52
    ังหวัด
    1.48
    у
    1.48
    醐
    1.43
     carpeta
    1.41
    PIT
    1.37
    బ్యా
    1.37
    श
    1.35
    ડ
    1.35
    PET
    1.34
    POSITIVE LOGITS
    m
    1.86
    ف
    1.84
    ie
    1.67
    м
    1.64
    ik
    1.63
     Rowling
    1.63
    ere
    1.59
    mz
    1.58
    k
    1.57
    ier
    1.52
    Activations Density 0.001%

    No Known Activations