© 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. 59077
    Prev
    Next
    INDEX
    Explanations

    specific word completions

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

    like me, little for, trying to

    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
    階
    0.47
    oru
    0.47
     Caedwalla
    0.47
    iew
    0.46
     Death
    0.45
    ></
    0.44
    endous
    0.44
    op
    0.44
    《
    0.43
    pet
    0.43
    POSITIVE LOGITS
     separator
    0.52
    ുവരി
    0.50
     perimeter
    0.49
    ᠮ
    0.47
     connues
    0.45
     calibrations
    0.45
     jeweler
    0.44
     ngờ
    0.44
    িনবার্গ
    0.44
     hasilnya
    0.44
    Activations Density 0.000%

    No Known Activations