© 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. 69790
    Prev
    Next
    INDEX
    Explanations

    action followed by context

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

    defining purpose or requirements

    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
     wraz
    0.49
     nonché
    0.48
     erschienen
    0.46
     എന്നിവ
    0.45
    ﺓ
    0.44
    ױ
    0.44
     Ін
    0.43
    ܫ
    0.43
    いました
    0.43
    État
    0.42
    POSITIVE LOGITS
     addon
    0.45
     Probation
    0.45
     receptors
    0.43
     only
    0.42
     Quarry
    0.42
     cages
    0.42
     either
    0.42
    只能
    0.42
     nii
    0.42
     reliever
    0.41
    Activations Density 0.004%

    No Known Activations