© 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. 203446
    Prev
    Next
    INDEX
    Explanations

    koreans imperativ verbs

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

    fibonacci series and common themes

    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
    ANCES
    0.53
    дно
    0.50
     antibiotic
    0.50
     入っ
    0.49
    на
    0.48
     行っ
    0.47
     変
    0.47
     麻
    0.47
    𝗹
    0.47
    ни
    0.47
    POSITIVE LOGITS
     ولكن
    0.46
    的同时
    0.46
    并行
    0.45
    uchtigkeit
    0.44
    olybdenum
    0.43
    apixel
    0.42
    后面
    0.42
     duración
    0.41
    uding
    0.40
     المرأة
    0.40
    Activations Density 0.001%

    No Known Activations