© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8625
    Prev
    Next
    INDEX
    Explanations

    linked in and Influence

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

    order status

    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_40_width_16k_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
    on
    0.51
    C
    0.47
    as
    0.47
    F
    0.44
    W
    0.43
    ay
    0.43
    win
    0.42
    G
    0.42
    R
    0.41
    way
    0.40
    POSITIVE LOGITS
     نمی
    0.38
     hvilket
    0.37
     diferentes
    0.36
     hör
    0.36
     suficient
    0.36
     evitando
    0.36
     nourriture
    0.35
     इसलिए
    0.35
     ultimi
    0.34
     اچھی
    0.34
    Activations Density 1.658%

    No Known Activations