© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12598
    Prev
    Next
    INDEX
    Explanations

    software/tech names followed by specifics

    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
     மாவட்டம்
    0.44
    <unused653>
    0.42
    ↵↵↵↵↵↵↵↵↵↵↵
    0.41
    <unused2117>
    0.40
    <unused2121>
    0.40
    iggins
    0.40
    <unused386>
    0.40
     સહિત
    0.38
    ⛷
    0.38
    <unused1016>
    0.38
    POSITIVE LOGITS
    ロゴ
    0.43
     ơi
    0.42
     Originals
    0.40
     nostru
    0.38
     logo
    0.38
    wide
    0.37
    Wiki
    0.36
    isms
    0.36
     propi
    0.36
     lingua
    0.36
    Activations Density 0.050%

    No Known Activations