© 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. 155469
    Prev
    Next
    INDEX
    Explanations

    commercial product, club, procedures, funds

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

    world concepts

    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
    MODULE
    0.51
    ਲ
    0.49
    爾
    0.49
    module
    0.49
    星期
    0.45
    так
    0.44
    ἥ
    0.44
    と
    0.43
    用
    0.43
    나
    0.43
    POSITIVE LOGITS
     stance
    0.43
     വ്യത്യ
    0.41
    BlockUsed
    0.41
     Enhanced
    0.41
     osób
    0.41
     osoby
    0.40
     دنیا
    0.40
     فترة
    0.40
     حی
    0.40
     osobe
    0.40
    Activations Density 0.004%

    No Known Activations