© 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. 110637
    Prev
    Next
    INDEX
    Explanations

    foreign language text

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

    communicating nationalists Traits stone AI choose strong

    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
    Otto
    0.49
    purse
    0.45
    Für
    0.44
    für
    0.44
    Stanley
    0.43
     مث
    0.41
    躲
    0.41
    !(
    0.41
    Maggie
    0.41
     HCP
    0.40
    POSITIVE LOGITS
    オンライン
    0.51
     Bewer
    0.48
     графи
    0.47
     putern
    0.47
    এই
    0.47
     Онлайн
    0.47
     caracteres
    0.46
     რომელიც
    0.46
     書き
    0.46
     Texto
    0.46
    Activations Density 0.001%

    No Known Activations