© 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. 90762
    Prev
    Next
    INDEX
    Explanations

    Ensemble with Directory

    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
     in
    0.51
    unek
    0.49
    from
    0.47
    вали
    0.47
    ίων
    0.47
    ও
    0.47
     मो
    0.46
    a
    0.46
    ຽງ
    0.46
     providing
    0.45
    POSITIVE LOGITS
     enjoin
    0.46
     террито
    0.45
     núcle
    0.45
    amir
    0.43
     TOW
    0.42
     চাকরি
    0.42
     ນ
    0.41
     שת
    0.41
     Chavan
    0.40
    égio
    0.40
    Activations Density 0.000%

    No Known Activations