© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4966
    Prev
    Next
    INDEX
    Explanations

    targeting or cover

    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_31_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
     accordingly
    0.36
    ations
    0.34
     яхшы
    0.34
    6
    0.34
     cheeses
    0.33
    ；
    0.33
    ப்புகள்
    0.33
     installations
    0.32
    திகள்
    0.32
    </td>
    0.32
    POSITIVE LOGITS
     უფრო
    0.50
     이번
    0.48
     більш
    0.46
     πιο
    0.44
     insidious
    0.44
    这次
    0.43
    這次
    0.43
     डायरेक्टली
    0.43
    이번
    0.43
     zusätzlichen
    0.42
    Activations Density 0.352%

    No Known Activations