© 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. 37029
    Prev
    Next
    INDEX
    Explanations

    home projects

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

    treating these fires

    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
     snatched
    0.49
     snatch
    0.46
     şark
    0.45
    localize
    0.43
    윽
    0.43
     monument
    0.43
    Télé
    0.42
    ဌ
    0.42
    ຈັດ
    0.41
    祂
    0.41
    POSITIVE LOGITS
    INO
    0.49
     amp
    0.48
     উদাহরণ
    0.46
     ino
    0.46
    <0xBA>
    0.44
    гти
    0.44
    ino
    0.43
    <0xB5>
    0.43
    ALLY
    0.43
    শালী
    0.43
    Activations Density 0.001%

    No Known Activations