© 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. 84208
    Prev
    Next
    INDEX
    Explanations

    woman made, agent who

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

    right to ask

    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
    썰
    0.46
    eel
    0.42
    an
    0.42
    as
    0.40
    NW
    0.40
    zelfde
    0.40
     및
    0.39
     detergents
    0.39
     coff
    0.39
    nak
    0.38
    POSITIVE LOGITS
     よく
    0.49
     あれ
    0.46
     همه
    0.46
    𝓪
    0.45
     वेरिए
    0.45
     Crossed
    0.45
     ჩატი
    0.45
    垕
    0.45
     હું
    0.44
    轻易
    0.44
    Activations Density 0.001%

    No Known Activations