© 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. 220147
    Prev
    Next
    INDEX
    Explanations

    descriptive words and their context

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

    handling practical advice

    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
    മം
    0.54
     ދ
    0.52
     ချ
    0.48
     Anosov
    0.47
     დ
    0.46
    zuki
    0.46
     الثانو
    0.46
    钚
    0.46
    超過
    0.46
     supera
    0.45
    POSITIVE LOGITS
     attributes
    0.45
    ब
    0.45
     sentiments
    0.43
    பா
    0.42
     рук
    0.41
    ード
    0.41
    पेश
    0.41
     опыта
    0.41
    τον
    0.41
    πον
    0.41
    Activations Density 0.000%

    No Known Activations