© 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. 125284
    Prev
    Next
    INDEX
    Explanations

    common words followed by punctuation or pronouns

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

    abstract, knowing, scrolled, dynamic IPs, woven fabrics, flange

    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
    ul
    0.51
    槊
    0.50
    uner
    0.45
    lens
    0.45
    utar
    0.44
    iser
    0.44
    timer
    0.44
    ansom
    0.44
    ermodel
    0.43
    ustan
    0.43
    POSITIVE LOGITS
    WARDS
    0.56
     Aéroport
    0.55
     plötzlich
    0.54
     दैट
    0.52
     ಆ
    0.49
    Ằ
    0.48
     ಎ
    0.47
     Persön
    0.47
     ಸಾಕ
    0.47
     António
    0.46
    Activations Density 0.001%

    No Known Activations