© 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. 226280
    Prev
    Next
    INDEX
    Explanations

    is followed by a word

    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
    ل
    0.49
     Koval
    0.47
    د
    0.46
     Bagi
    0.46
    νε
    0.46
    ట్టు
    0.46
    ستخدم
    0.45
    ومات
    0.45
     jurisprudence
    0.44
    امر
    0.44
    POSITIVE LOGITS
    )=\
    0.50
     untrue
    0.50
     मुसीबत
    0.49
     unsightly
    0.49
     равна
    0.48
     тру
    0.47
     す
    0.47
     второй
    0.47
     сосед
    0.47
     другой
    0.46
    Activations Density 0.000%

    No Known Activations