© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16079
    Prev
    Next
    INDEX
    Explanations

    Classifieds, treatments, information

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

    ' quoting text

    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
    espoir
    0.38
     días
    0.35
     merda
    0.35
    YE
    0.35
    زه
    0.35
     noches
    0.35
    ؤ
    0.34
     día
    0.34
    omás
    0.34
     vida
    0.33
    POSITIVE LOGITS
    <unused1851>
    0.45
    <unused1910>
    0.44
    <unused450>
    0.42
    <unused557>
    0.42
    <unused209>
    0.41
    <unused501>
    0.41
     використову
    0.41
    <unused402>
    0.41
    <unused544>
    0.41
    <unused680>
    0.40
    Activations Density 0.003%

    No Known Activations