© 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. 135609
    Prev
    Next
    INDEX
    Explanations

    website, domain, sculpture, Reproduction, Snapcode

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

    understood that

    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
    數
    0.57
    ⑶
    0.56
    degener
    0.53
    tm
    0.52
    বস্ত
    0.52
    cnt
    0.52
    τως
    0.52
     بعض
    0.51
    ⑸
    0.51
    væ
    0.50
    POSITIVE LOGITS
     Men
    0.57
     verb
    0.57
     holiday
    0.55
     payroll
    0.52
     Spanish
    0.51
     Holiday
    0.50
     Payroll
    0.50
     texts
    0.49
     Verb
    0.49
     Post
    0.49
    Activations Density 0.001%

    No Known Activations