© 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. 71597
    Prev
    Next
    INDEX
    Explanations

    strong prison, loan, gas

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

    links, tools, or definitions

    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
     தற்போது
    0.52
     к
    0.46
     indignant
    0.46
     Persona
    0.45
     กำ
    0.45
     speculating
    0.44
    をしている
    0.43
     pretending
    0.43
    EqualTo
    0.43
    ल्फ
    0.42
    POSITIVE LOGITS
    ాలే
    0.45
    ಂತ್ರಿ
    0.45
    ুনের
    0.44
    olare
    0.43
    ahertz
    0.43
     ব্যব
    0.42
    철
    0.41
    polymer
    0.41
    下来的
    0.41
    oxyde
    0.41
    Activations Density 0.000%

    No Known Activations