© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 292
    Prev
    Next
    INDEX
    Explanations

    just [key]: string

    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
     prostor
    -0.84
    ילת
    -0.82
     deliciously
    -0.81
    我慢
    -0.80
     alcuni
    -0.79
    Ost
    -0.79
    部分が
    -0.77
    が付いて
    -0.77
     Cello
    -0.76
     Antwerpen
    -0.76
    POSITIVE LOGITS
    LONG
    0.77
     Just
    0.77
    널
    0.73
    Just
    0.72
     Like
    0.72
    قام
    0.71
    just
    0.70
     Having
    0.68
     placing
    0.68
     JUST
    0.68
    Activations Density 0.064%

    No Known Activations