© 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. 247846
    Prev
    Next
    INDEX
    Explanations

    POS, continuous, convention, hardly, like, from, him

    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
    ATT
    0.53
    ৫
    0.51
    妹妹
    0.49
    wink
    0.49
     وصحبه
    0.48
     CIVIL
    0.47
    el
    0.47
    RAW
    0.47
    搖
    0.46
    त
    0.46
    POSITIVE LOGITS
     soliton
    0.50
    ندگی
    0.47
     어떤
    0.47
     llamada
    0.46
     Bolton
    0.45
     sagen
    0.44
     leucine
    0.43
     kuru
    0.43
     histidine
    0.43
    ถุนายน
    0.42
    Activations Density 0.000%

    No Known Activations