© 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. 74689
    Prev
    Next
    INDEX
    Explanations

    charging or refunding items

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

    merchants and sailors

    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
     Küh
    0.49
     mortem
    0.47
     Lordships
    0.47
    铭
    0.45
     indoctr
    0.45
     условии
    0.44
     parr
    0.44
     Balfour
    0.44
     effluent
    0.43
     $\%$
    0.43
    POSITIVE LOGITS
    te
    0.48
    alle
    0.48
    navigation
    0.47
    metrics
    0.46
    effective
    0.45
    approximation
    0.45
    nacht
    0.45
     अनेक
    0.45
     ইন্টারনেট
    0.45
    surfing
    0.44
    Activations Density 0.001%

    No Known Activations