© 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. 247750
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    _
    0.58
    Values
    0.47
    LAY
    0.47
    ancos
    0.46
    1
    0.46
    positive
    0.45
     Values
    0.45
     Minimum
    0.45
    POSITIVE
    0.45
    де
    0.44
    POSITIVE LOGITS
     امد
    0.48
    मक
    0.46
    wier
    0.46
    éth
    0.45
     führen
    0.44
    imizde
    0.44
    <0xB2>
    0.44
    oną
    0.43
    inom
    0.42
    깜
    0.41
    Activations Density 0.000%

    No Known Activations