© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 190144
    Prev
    Next
    INDEX
    Explanations

    published features, buy services

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

    company, Blue, available

    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
    レ
    0.47
    트
    0.45
    itches
    0.45
    ляем
    0.45
    st
    0.44
    K
    0.44
    یره
    0.43
    ங்கம்
    0.43
    란
    0.43
    앓
    0.43
    POSITIVE LOGITS
     Međ
    0.62
     acquire
    0.55
     Umsatz
    0.55
    vorschau
    0.52
     skapa
    0.52
     Timatic
    0.51
     çarp
    0.50
     
    0.49
     članak
    0.49
     bárm
    0.49
    Activations Density 0.000%

    No Known Activations