© 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. 197738
    Prev
    Next
    INDEX
    Explanations

    preference for exploration

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

    explaining structure or sequence

    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
    标准
    0.48
    ologico
    0.47
    ┄
    0.45
    帜
    0.45
    nCount
    0.44
    WithDictionary
    0.44
    count
    0.43
    纱
    0.42
    行为
    0.42
     الوط
    0.42
    POSITIVE LOGITS
     explor
    0.48
     entdecken
    0.47
     思っ
    0.47
     मुली
    0.46
     manfaat
    0.45
     zeigen
    0.42
     mostrar
    0.41
     montrer
    0.41
     núcle
    0.41
     விய
    0.41
    Activations Density 0.000%

    No Known Activations