© 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. 182430
    Prev
    Next
    INDEX
    Explanations

    ghost names

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

    "with two", "have a"

    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
    CreateIndex
    0.50
    प्या
    0.48
    ص
    0.46
    צ
    0.45
    opportunities
    0.45
    荣誉
    0.44
    pail
    0.44
    逈
    0.44
    ம்பர்
    0.43
    閎
    0.43
    POSITIVE LOGITS
     factor
    0.49
     Führ
    0.49
    0.49
     ghost
    0.47
     Shao
    0.46
     ..."
    0.46
    )}$
    0.45
     AEG
    0.44
     Ghost
    0.43
     ɛ
    0.43
    Activations Density 0.000%

    No Known Activations