© 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. 49265
    Prev
    Next
    INDEX
    Explanations

    enjoy

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

    health costs

    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
     éléments
    0.53
    埶
    0.53
     له
    0.52
    فضل
    0.51
     إذا
    0.51
     especiales
    0.51
     eszköz
    0.51
     النظر
    0.51
     év
    0.50
     形
    0.50
    POSITIVE LOGITS
    agree
    0.46
    ृह
    0.44
    ostridium
    0.43
    ">
    0.43
    intended
    0.42
    きの
    0.41
     लापता
    0.41
    output
    0.40
    ंबई
    0.40
    いが
    0.40
    Activations Density 0.000%

    No Known Activations