© 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. 178917
    Prev
    Next
    INDEX
    Explanations

    desired outcomes

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

    descriptions of choices

    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
    कालिक
    0.55
    ucha
    0.52
    iva
    0.51
     если
    0.51
    át
    0.49
    ático
    0.49
     ی
    0.48
    adan
    0.48
    jde
    0.47
     национа
    0.47
    POSITIVE LOGITS
     원하는
    0.46
     sculpting
    0.45
    Scul
    0.45
     desired
    0.44
    벌
    0.43
    ould
    0.42
    তাকে
    0.42
     \""
    0.42
     squeez
    0.41
    ربة
    0.41
    Activations Density 0.000%

    No Known Activations