© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31824
    Prev
    Next
    INDEX
    Explanations

    code structure or data labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    3
    0.79
    5
    0.72
    7
    0.71
    0
    0.68
    2
    0.67
    the
    0.67
    1
    0.65
    4
    0.64
    op
    0.64
    6
    0.64
    POSITIVE LOGITS
    ،
    0.63
    )،
    0.60
     vraie
    0.56
     extraordinaire
    0.56
    ﭜ
    0.54
     inwoners
    0.53
    ၊
    0.51
     mauvaise
    0.51
    ༸
    0.51
    ﮈ
    0.50
    Activations Density 0.023%

    No Known Activations