© 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. 17000
    Prev
    Next
    INDEX
    Explanations

    format, brand, best, tomato

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

    Simple Components

    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
    ها
    0.49
     som
    0.47
    getVisibility
    0.47
     bruising
    0.47
     bru
    0.46
    j
    0.45
    acions
    0.45
     dvs
    0.45
    ısıyla
    0.44
     hany
    0.44
    POSITIVE LOGITS
     사회
    0.58
     기업
    0.49
     금융
    0.48
     இயக்கு
    0.48
     учены
    0.47
    ゾ
    0.47
     ಸಾಮಾ
    0.47
     করিতেছিল
    0.46
     парламент
    0.46
     thinkers
    0.45
    Activations Density 0.000%

    No Known Activations