© 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. 159379
    Prev
    Next
    INDEX
    Explanations

    dad walks, depression, continue to

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

    items or prompts

    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
     ඔහු
    0.47
    };
    0.47
     hormon
    0.46
     भाई
    0.46
     असून
    0.44
     항상
    0.42
     koska
    0.42
     ভাই
    0.41
     perce
    0.41
     Mitchell
    0.41
    POSITIVE LOGITS
    ান্ট
    0.48
     abstractions
    0.46
    남
    0.45
    ям
    0.45
    aun
    0.45
    isent
    0.44
    chaften
    0.43
    황
    0.42
    mUserManager
    0.42
    ቦ
    0.42
    Activations Density 0.000%

    No Known Activations