© 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. 242003
    Prev
    Next
    INDEX
    Explanations

    construction equipment business

    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
    시간
    0.49
     milliers
    0.46
    회가
    0.46
    كس
    0.45
    umna
    0.45
    왔
    0.44
    সি
    0.43
    dropBtn
    0.43
    ွား
    0.43
    सौ
    0.43
    POSITIVE LOGITS
     அல்லது
    0.49
    i
    0.48
    Insect
    0.46
    aing
    0.46
    oting
    0.45
    logging
    0.45
     ამ
    0.45
    insect
    0.45
    หรือ
    0.45
    oucault
    0.44
    Activations Density 0.001%

    No Known Activations