© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77173
    Prev
    Next
    INDEX
    Explanations

    convert to or into

    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
    全ての
    -1.09
    妇女
    -1.02
     모든
    -0.97
     REPUBLIC
    -0.93
    不喜欢
    -0.93
    possibly
    -0.90
    rogen
    -0.88
     favoriser
    -0.88
    āb
    -0.87
    ಲ್
    -0.85
    POSITIVE LOGITS
     their
    1.63
     into
    1.49
     its
    1.45
     corresponding
    1.38
     something
    1.36
     a
    1.34
     usable
    1.29
     another
    1.20
     equivalent
    1.20
     appropriate
    1.19
    Activations Density 0.116%

    No Known Activations