© 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. 84164
    Prev
    Next
    INDEX
    Explanations

    calling base constructor

    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
    );
    0.49
    members
    0.47
    this
    0.46
    base
    0.45
    now
    0.43
    bases
    0.42
    listeners
    0.41
    streets
    0.40
    nings
    0.39
    mainframe
    0.39
    POSITIVE LOGITS
     Quando
    0.44
     وكانت
    0.44
    ↵↵↵↵↵↵↵↵
    0.39
     શહે
    0.38
     verhindern
    0.38
     Frieden
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
     uy
    0.37
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.37
     gestalt
    0.37
    Activations Density 0.000%

    No Known Activations