© 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. 185820
    Prev
    Next
    INDEX
    Explanations

    goods, friendly, Kyoto, Watson, purchasing, key, different, leading, customer needs, direction

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

    unreliable or occasional

    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
     funções
    0.54
    داء
    0.48
    هاء
    0.48
     persu
    0.46
    ك
    0.45
     capacità
    0.44
    測試
    0.44
     आजमा
    0.44
     derivadas
    0.43
    視覺
    0.43
    POSITIVE LOGITS
    alles
    0.50
    Funny
    0.48
    erne
    0.48
    iniert
    0.48
    issen
    0.47
    akter
    0.47
    abelle
    0.46
    и
    0.46
     Dionys
    0.45
    isiert
    0.45
    Activations Density 0.001%

    No Known Activations