© 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. 66214
    Prev
    Next
    INDEX
    Explanations

    nightly dd-wrt builds

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

    post-training or after

    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
     δεύτε
    0.52
    iliśmy
    0.47
    úng
    0.46
    ଞ
    0.46
    ünüz
    0.44
    ’
    0.43
    어야
    0.42
    netHex
    0.42
    た
    0.42
    ini
    0.42
    POSITIVE LOGITS
     Respondents
    0.50
     Peoples
    0.49
    с
    0.49
     दुनियाभर
    0.48
     Leading
    0.46
    лед
    0.46
     Wem
    0.45
     selain
    0.45
     Bao
    0.45
    都能
    0.44
    Activations Density 0.001%

    No Known Activations