© 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. 139222
    Prev
    Next
    INDEX
    Explanations

    custom imprint or manufacture

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

    code logic recommendation

    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
    がん
    0.49
    γη
    0.45
    טה
    0.45
     상당히
    0.44
    सि
    0.43
    gly
    0.42
    ক
    0.42
    Titanic
    0.41
    酵素
    0.41
    тно
    0.41
    POSITIVE LOGITS
    㵴
    0.52
     سر
    0.51
     lutego
    0.51
    检测
    0.49
     dobbiamo
    0.48
     Brest
    0.48
     znam
    0.48
     حمد
    0.48
     Dezember
    0.47
     Sabemos
    0.47
    Activations Density 0.000%

    No Known Activations