© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13340
    Prev
    Next
    INDEX
    Explanations

    news dispatch indicator

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

    describing specific states

    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_16k_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
     ду
    0.53
     באמצעות
    0.49
     перено
    0.47
    자에
    0.47
    ুরী
    0.46
     ער
    0.45
     алге
    0.45
     에
    0.45
     ט
    0.45
    嘣
    0.44
    POSITIVE LOGITS
     mar
    0.51
     central
    0.46
     ko
    0.45
     memory
    0.44
    central
    0.43
     become
    0.42
     chance
    0.42
     political
    0.42
    mio
    0.42
     multicellular
    0.42
    Activations Density 0.004%

    No Known Activations