© 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. 143044
    Prev
    Next
    INDEX
    Explanations

    preserving, converting, coordinator, cheese, dramatic

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

    slightly unhinged/harsh

    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
    やっぱり
    0.58
     متنوع
    0.51
    FANG
    0.50
    항공
    0.49
    ༎
    0.49
    ള
    0.47
    さまざまな
    0.47
    ಲ
    0.47
    뮐
    0.46
    Literatur
    0.45
    POSITIVE LOGITS
     jars
    0.46
    rif
    0.46
     enroll
    0.45
     equilibrio
    0.45
     pude
    0.44
     strtoupper
    0.44
     rol
    0.43
     jar
    0.43
     enrolling
    0.43
     convuls
    0.43
    Activations Density 0.001%

    No Known Activations