© 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. 134812
    Prev
    Next
    INDEX
    Explanations

    minerals and caramel

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

    generated text and code sequences

    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
     بلو
    0.60
     SMP
    0.44
    ించ
    0.44
     gladi
    0.44
     تسم
    0.43
     글로
    0.43
     بلا
    0.43
    视
    0.42
     떠
    0.42
    acjach
    0.42
    POSITIVE LOGITS
     Все
    0.50
    ณ
    0.49
    ς
    0.48
    ២
    0.48
    これらの
    0.47
     વિશ
    0.47
     einges
    0.46
    嗎
    0.46
     с
    0.46
     complying
    0.46
    Activations Density 0.002%

    No Known Activations