© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98097
    Prev
    Next
    INDEX
    Explanations

    Nid, Nide, ID, NID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    👰
    -0.73
     autistic
    -0.72
     朝
    -0.65
     Polskiej
    -0.65
     panty
    -0.64
     přev
    -0.63
     dusted
    -0.63
     повер
    -0.61
     Zürich
    -0.61
     Above
    -0.61
    POSITIVE LOGITS
    BSA
    0.77
     benötigt
    0.74
    Full
    0.73
    released
    0.72
    ceded
    0.71
     розо
    0.71
     lateinit
    0.70
     marginally
    0.70
    orghe
    0.68
    martre
    0.68
    Activations Density 0.031%

    No Known Activations