© 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. 70332
    Prev
    Next
    INDEX
    Explanations

    floor number signs

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

    specific words and phrases

    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
    ඕ
    0.48
    Ⲟ
    0.48
     તરફ
    0.48
    wald
    0.43
     பெற
    0.42
     flawlessly
    0.42
    Օ
    0.42
     он
    0.42
    yaf
    0.42
     ສ
    0.41
    POSITIVE LOGITS
    抱
    0.45
     Quantum
    0.44
     pond
    0.43
     Arithmetic
    0.43
    漕
    0.43
     जिनको
    0.41
    一块
    0.41
    但是在
    0.41
     Speech
    0.40
     Semantic
    0.40
    Activations Density 0.000%

    No Known Activations