© 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. 74228
    Prev
    Next
    INDEX
    Explanations

    contextual phrases

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

    definition and description

    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
     سابق
    0.46
    년을
    0.46
     遊ん
    0.46
     সংজ্ঞা
    0.45
    }}$,
    0.44
    ן
    0.44
    எஸ்
    0.44
    }}$.
    0.43
     선택
    0.43
    nimmt
    0.43
    POSITIVE LOGITS
    ра
    0.44
     boots
    0.40
    ൂ
    0.40
     Expenses
    0.39
     narcotics
    0.39
     lifestyle
    0.39
     pint
    0.39
     roulette
    0.39
    Setter
    0.38
    റ്റു
    0.38
    Activations Density 0.004%

    No Known Activations