© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151337
    Prev
    Next
    INDEX
    Explanations

    body structures and residues

    np_acts-logits-general · gemini-2.5-flash-lite

    position and selling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    问题
    0.57
     problem
    0.48
     星
    0.45
     됩니다
    0.45
     问题
    0.45
     本
    0.44
    这个
    0.44
     integrity
    0.44
    感
    0.43
    र
    0.43
    POSITIVE LOGITS
     furent
    0.55
     объяви
    0.50
     criticised
    0.50
     были
    0.46
    krank
    0.46
     buvo
    0.46
     правительства
    0.46
    وكان
    0.46
    became
    0.46
     refrained
    0.46
    Activations Density 0.000%

    No Known Activations