© 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. 7928
    Prev
    Next
    INDEX
    Explanations

    fundamental basis or starting point

    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
    L
    0.58
    מ
    0.57
     ansiedad
    0.51
     d
    0.50
    ل
    0.48
    a
    0.48
    ’
    0.48
     dando
    0.47
    s
    0.47
    D
    0.47
    POSITIVE LOGITS
    ਾਰ
    0.58
    ة
    0.54
    下旬
    0.50
     depository
    0.50
    <unused2172>
    0.49
    iculation
    0.48
     preschoolers
    0.48
    薢
    0.48
    erweise
    0.47
     ″
    0.47
    Activations Density 0.799%

    No Known Activations