© 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. 47021
    Prev
    Next
    INDEX
    Explanations

    names followed by maiden names

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

    female names and family names

    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
    Daddy
    0.49
     Daddy
    0.46
     Administrative
    0.44
    ➳
    0.42
     Metallurgy
    0.42
     Sailors
    0.41
     Memorial
    0.41
     Paintings
    0.41
     Kayla
    0.40
    Administrative
    0.40
    POSITIVE LOGITS
     pals
    0.42
    フ
    0.40
     なる
    0.38
     გავ
    0.38
     ரீ
    0.36
    ブ
    0.36
    ラル
    0.35
    誘導
    0.35
    ギ
    0.35
     pas
    0.35
    Activations Density 0.010%

    No Known Activations