© 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. 150205
    Prev
    Next
    INDEX
    Explanations

    child safety and well-being

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

    candle is lit, dangerous

    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
     TRAVEL
    0.44
    拿出
    0.43
     प्रदूषण
    0.42
    꼰
    0.41
     戦
    0.40
     シューズ
    0.40
     NATURE
    0.39
     Graffiti
    0.39
    ၁
    0.39
     Букмекер
    0.39
    POSITIVE LOGITS
    睡
    0.49
    ailure
    0.41
     giấc
    0.41
     unsupervised
    0.40
     deadly
    0.40
    omicide
    0.39
     household
    0.39
    oters
    0.39
     overdose
    0.39
    腐
    0.38
    Activations Density 0.070%

    No Known Activations