© 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. 33454
    Prev
    Next
    INDEX
    Explanations

    dumbbells

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

    specific nouns and terms

    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
    ica
    0.50
    ník
    0.49
    έα
    0.48
    सामान्य
    0.48
    齙
    0.46
    ก
    0.46
    ሦ
    0.46
     फुलकारी
    0.45
     ሙሉ
    0.45
    畱
    0.45
    POSITIVE LOGITS
     Fong
    0.43
     synthesizer
    0.40
     closeness
    0.39
     teori
    0.39
     atmósfera
    0.39
     subsidies
    0.38
     altitudes
    0.38
     Sabtu
    0.38
     publicized
    0.38
     sogar
    0.38
    Activations Density 0.000%

    No Known Activations