© 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. 151907
    Prev
    Next
    INDEX
    Explanations

    lime juice

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

    Scottish cities

    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
     چاہئے
    0.47
    ൈ
    0.44
    زش
    0.43
    >$
    0.42
    OrEqualTo
    0.42
    :‏
    0.42
    GALAD
    0.42
    ByName
    0.41
    运维
    0.41
     chairperson
    0.41
    POSITIVE LOGITS
     Vom
    0.48
     Scottish
    0.47
    oski
    0.46
    சார்
    0.46
     Scot
    0.46
     익
    0.45
     ZX
    0.44
     IJ
    0.44
     Zheng
    0.44
    Scottish
    0.44
    Activations Density 0.000%

    No Known Activations