© 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. 62147
    Prev
    Next
    INDEX
    Explanations

    services, commerce, technology

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

    lists with a dot

    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
    匕
    0.41
    학년
    0.40
    痙
    0.40
    苋
    0.39
    假設
    0.39
     цело
    0.39
     popOperand
    0.38
    㐫
    0.38
    থমে
    0.38
     кора
    0.38
    POSITIVE LOGITS
    💰
    0.49
     captivating
    0.49
     services
    0.49
     hizmet
    0.47
     smartphone
    0.47
     cashback
    0.47
     পরিষেবা
    0.46
     enchanting
    0.46
     smartphones
    0.46
     स्वामित्व
    0.46
    Activations Density 0.001%

    No Known Activations