© 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. 16741
    Prev
    Next
    INDEX
    Explanations

    microsoft

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

    import paths

    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
     octubre
    0.47
     വ്യക്തി
    0.41
    香味
    0.40
    igne
    0.39
     febrero
    0.39
    瓤
    0.39
    ുമുള്ള
    0.39
    रेटर
    0.38
     Wicklow
    0.38
     হোল
    0.38
    POSITIVE LOGITS
     근
    0.43
     ການ
    0.41
    ־
    0.41
    ্ম্ম
    0.39
     ভট্ট
    0.38
    வதன்
    0.38
     الع
    0.36
    劧
    0.36
    ایا
    0.36
    ్
    0.36
    Activations Density 0.000%

    No Known Activations