© 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. 246527
    Prev
    Next
    INDEX
    Explanations

    timeframe, theme, same

    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
     IANS
    0.59
     introns
    0.47
     exons
    0.47
     housed
    0.47
     ARIMA
    0.44
    腸
    0.44
    फान
    0.44
     यूं
    0.43
     FTSE
    0.43
    ческим
    0.43
    POSITIVE LOGITS
    ati
    0.51
     மட்டும்
    0.50
    orative
    0.46
    ala
    0.41
    atform
    0.40
     แบบ
    0.40
     ala
    0.40
    em
    0.39
     outweighs
    0.39
     或
    0.39
    Activations Density 0.000%

    No Known Activations