© 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. 69891
    Prev
    Next
    INDEX
    Explanations

    user interface and identity

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

    Unity UI code

    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
    لا
    0.49
    醾
    0.49
    osexual
    0.48
    ไม่ใช่
    0.44
     आतंकवादी
    0.43
     центра
    0.42
    不够
    0.42
    い
    0.41
     არ
    0.41
     эк
    0.41
    POSITIVE LOGITS
    by
    0.49
    the
    0.49
     representada
    0.46
    custom
    0.44
    compress
    0.44
    commands
    0.43
    cando
    0.43
    transfer
    0.43
    decrement
    0.43
    created
    0.42
    Activations Density 0.000%

    No Known Activations