© 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. 143923
    Prev
    Next
    INDEX
    Explanations

    preceding words

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

    previous or former

    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
    ts
    0.54
    ras
    0.48
    J
    0.48
     J
    0.47
    w
    0.47
     Zij
    0.45
    ib
    0.45
    ok
    0.44
    াতা
    0.44
    am
    0.44
    POSITIVE LOGITS
     wcześniej
    0.52
     poprzed
    0.52
     முன்னர்
    0.51
     봤
    0.50
     সন্তানদের
    0.49
     già
    0.49
     tidigare
    0.48
     ehemaligen
    0.48
     scritto
    0.48
    듦
    0.47
    Activations Density 0.000%

    No Known Activations