© 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. 233745
    Prev
    Next
    INDEX
    Explanations

    basis recognition

    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
    銀
    0.48
    ium
    0.46
    0.45
    בר
    0.45
    間に
    0.44
    در
    0.43
    لما
    0.43
     середине
    0.42
    evil
    0.41
    い
    0.41
    POSITIVE LOGITS
     própri
    0.57
     Basis
    0.50
     recognises
    0.48
     SWOT
    0.48
    ври
    0.48
     basis
    0.47
    zną
    0.47
     Appe
    0.46
     begrü
    0.46
     próp
    0.46
    Activations Density 0.001%

    No Known Activations