© 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. 9606
    Prev
    Next
    INDEX
    Explanations

    algorithms modeled

    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
     veik
    0.38
    誤
    0.37
    ñal
    0.36
     coefficients
    0.35
     anatomical
    0.35
     fevere
    0.35
     mule
    0.35
     shrew
    0.35
     dus
    0.34
     podría
    0.34
    POSITIVE LOGITS
    Defining
    0.37
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
    জ্ঞা
    0.35
    ↵↵↵↵↵
    0.35
    RANK
    0.35
    </h2>
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
     ،
    0.34
    꾸
    0.33
    Repos
    0.33
    Activations Density 0.000%

    No Known Activations