© 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. 38911
    Prev
    Next
    INDEX
    Explanations

    conditional phrases

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

    languages, conditional, guidance

    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
    분
    0.47
    簡單
    0.46
    사
    0.46
     किताबों
    0.44
    र
    0.42
    𝗱
    0.42
    ⚙
    0.42
    简单
    0.42
    IVES
    0.41
    透過
    0.41
    POSITIVE LOGITS
     sarebbe
    0.53
     wäre
    0.52
     sería
    0.50
     would
    0.49
     mondiale
    0.49
     serait
    0.48
    的研究
    0.47
     avrebbe
    0.45
     ещё
    0.44
    ന്ത്രാ
    0.43
    Activations Density 0.000%

    No Known Activations