© 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. 201507
    Prev
    Next
    INDEX
    Explanations

    second, third, dressing

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

    technical possibility, new color

    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
     Hatteras
    0.49
     mustache
    0.47
    bios
    0.45
     ט
    0.44
    船舶
    0.44
     handicrafts
    0.44
     ideologies
    0.43
     बायो
    0.43
    enna
    0.42
     biodegradable
    0.42
    POSITIVE LOGITS
    𝘆
    0.48
    ৭
    0.47
    ৌজ
    0.46
    ಂಜ
    0.44
     colon
    0.44
    ನಿಯ
    0.44
    ৯
    0.43
    ここまで
    0.42
    ัน
    0.42
    ٩
    0.42
    Activations Density 0.000%

    No Known Activations