© 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. 20700
    Prev
    Next
    INDEX
    Explanations

    protector against, creator god

    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
     ladle
    0.43
     celé
    0.43
    тория
    0.42
     already
    0.39
    Pts
    0.39
    醛
    0.39
    ia
    0.39
    ňuje
    0.39
     subtlety
    0.38
     millennia
    0.38
    POSITIVE LOGITS
     depicting
    0.55
    ２
    0.54
     Also
    0.52
    }
    0.52
    ອກ
    0.49
    /"
    0.49
    2
    0.46
    ，
    0.46
     également
    0.46
    角色
    0.46
    Activations Density 0.000%

    No Known Activations