© 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. 46543
    Prev
    Next
    INDEX
    Explanations

    saw firsthand

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

    git background inspection training

    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
    FileInputStream
    0.44
     روب
    0.41
    niger
    0.41
     {})
    0.40
    lom
    0.39
    uppe
    0.39
    iri
    0.38
    ibe
    0.38
    irish
    0.38
    MyHomePage
    0.38
    POSITIVE LOGITS
    δου
    0.52
     πως
    0.51
     quá
    0.50
    Ἠ
    0.49
    ᓇ
    0.48
    当社
    0.48
    ˍ
    0.48
     Αυ
    0.48
    😮
    0.48
     SECOND
    0.47
    Activations Density 0.000%

    No Known Activations