© 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. 31-GEMMASCOPE-2-RES-262K
    7. 128681
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
    ikap
    0.49
    保持
    0.48
    irp
    0.48
    概
    0.46
    Kap
    0.45
    కాలు
    0.45
    肢
    0.44
    ార్లు
    0.44
    延
    0.44
     Xiao
    0.43
    POSITIVE LOGITS
     اٹ
    0.48
     molten
    0.46
     sledge
    0.46
     금
    0.45
     déchets
    0.45
     jewellery
    0.45
     oils
    0.45
     interd
    0.44
     interleukin
    0.44
     ダイヤモンド
    0.43
    Activations Density 0.002%

    No Known Activations