© 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. 234220
    Prev
    Next
    INDEX
    Explanations

    new way, hair clips, phone number, weather stripping

    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
    0.51
     день
    0.47
     suppress
    0.47
     حقی
    0.44
     Blossom
    0.43
     সেদিন
    0.42
     literally
    0.42
     reincarn
    0.42
    น
    0.41
    act
    0.41
    POSITIVE LOGITS
     Ärzte
    0.48
    ᱮ
    0.47
    ʢ
    0.46
    צה
    0.46
     clínicos
    0.46
    ပါ။
    0.45
    짖
    0.45
     ruộng
    0.45
     indique
    0.45
     inversión
    0.44
    Activations Density 0.001%

    No Known Activations