© 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. 143107
    Prev
    Next
    INDEX
    Explanations

    expands when, construction sites

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

    common sequence load

    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
     hac
    0.47
     Average
    0.47
    )
    0.46
    riti
    0.45
    ())
    0.43
     Consequently
    0.43
     informado
    0.43
    isati
    0.43
     रिपीट
    0.42
     inform
    0.42
    POSITIVE LOGITS
    بيع
    0.47
     مليار
    0.46
     realidade
    0.44
    كنولوجيا
    0.44
    ंबू
    0.43
    درسة
    0.42
     metallurgy
    0.42
    ϋ
    0.42
     अध्याय
    0.42
    ڠ
    0.42
    Activations Density 0.001%

    No Known Activations