© 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. 101483
    Prev
    Next
    INDEX
    Explanations

    time, numbers, dates

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

    code imports

    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
     فرص
    0.45
    chromosome
    0.44
    的机会
    0.44
    โอกาส
    0.43
     अवसर
    0.43
    栝
    0.43
    opportunity
    0.43
    Ỹ
    0.43
    wedge
    0.42
    Severe
    0.40
    POSITIVE LOGITS
     değiştir
    0.45
     nascost
    0.45
     coleta
    0.45
     tarot
    0.44
     inicial
    0.44
     onChange
    0.43
    onChange
    0.43
     escond
    0.42
     bulldoz
    0.42
     supabase
    0.41
    Activations Density 0.001%

    No Known Activations