© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 368
    Prev
    Next
    INDEX
    Explanations

    grandma and windows serial numbers

    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
    ien
    1.36
    蹤
    1.32
     bố
    1.27
     dotyczą
    1.25
     weißen
    1.25
     devastating
    1.22
    eer
    1.22
     disastrous
    1.22
    ında
    1.21
    ilise
    1.21
    POSITIVE LOGITS
    с
    1.67
    '
    1.27
    Although
    1.23
     aches
    1.22
    '
    1.22
     RCW
    1.21
     XRD
    1.20
     approximates
    1.20
    อ่าน
    1.18
    ла
    1.17
    Activations Density 0.002%

    No Known Activations