© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1253
    Prev
    Next
    INDEX
    Explanations

    Future technical contexts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
     सुनाई
    0.50
     alguien
    0.49
    ángulo
    0.48
    abilirsiniz
    0.48
    iyorum
    0.47
    咘
    0.47
    两人
    0.46
    还是很
    0.46
     ไหร่
    0.45
    อยาก
    0.45
    POSITIVE LOGITS
     SF
    0.48
     innovative
    0.43
     S
    0.42
     M
    0.40
     T
    0.39
     V
    0.39
    <0xC2>
    0.39
     extensive
    0.39
     Inclusion
    0.39
     የአ
    0.38
    Activations Density 0.000%

    No Known Activations