© 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. 204809
    Prev
    Next
    INDEX
    Explanations

    finance and insurance plans

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

    calculate total liabilities

    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
    throughput
    0.51
    tikzpicture
    0.47
    ».
    0.46
    যদি
    0.46
    」。
    0.46
    int
    0.44
    ]).
    0.43
     ذہ
    0.43
     床
    0.43
    STOR
    0.41
    POSITIVE LOGITS
    Resultado
    0.49
     Mori
    0.47
     éc
    0.47
    ंबू
    0.47
    ñez
    0.45
     Samp
    0.45
     Morr
    0.45
     matematik
    0.44
     Ambos
    0.44
    喆
    0.44
    Activations Density 0.001%

    No Known Activations