© 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. 227379
    Prev
    Next
    INDEX
    Explanations

    2 euro, floor unit, website with

    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
    7
    0.54
    2
    0.54
    3
    0.52
    4
    0.52
     sette
    0.51
     şekilde
    0.49
     daca
    0.49
    9
    0.49
     seis
    0.48
    d
    0.48
    POSITIVE LOGITS
    这个
    0.43
    γεν
    0.43
    ρικ
    0.43
    ционными
    0.42
    地址
    0.42
    成为了
    0.42
    െടുത്ത
    0.42
    hadoop
    0.40
    ∪
    0.40
    ূতন
    0.40
    Activations Density 0.000%

    No Known Activations