© 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. 251
    Prev
    Next
    INDEX
    Explanations

    understand the

    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
    RO
    1.23
    R
    1.23
    D
    1.11
    ↵
    1.09
    T
    1.09
    RA
    1.09
    SON
    1.02
    S
    0.98
    RI
    0.95
    Ss
    0.94
    POSITIVE LOGITS
     conocimientos
    1.23
     tentang
    1.22
     अबाउट
    1.22
    ovka
    1.18
     जानकारियां
    1.18
     conocimiento
    1.17
     about
    1.16
     acerca
    1.16
    知识
    1.14
    knowledge
    1.14
    Activations Density 1.555%

    No Known Activations