© 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
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241348
    Prev
    Next
    INDEX
    Explanations

    diverse topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     —
    0.59
     hyphen
    0.57
     dropout
    0.56
     mask
    0.56
     merged
    0.55
     amin
    0.55
     appending
    0.55
    iten
    0.54
     directory
    0.54
    ZERO
    0.54
    POSITIVE LOGITS
     وقلنا
    0.60
     informação
    0.57
    司令
    0.55
     богат
    0.55
    ായിക
    0.54
    慄
    0.53
    🎠
    0.53
    ணம்
    0.51
    Cic
    0.51
    🌷
    0.51
    Activations Density 0.000%

    No Known Activations