© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57683
    Prev
    Next
    INDEX
    Explanations

    `--SKIPIF--`

    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
    umbuhan
    -0.69
    HARR
    -0.67
     reactants
    -0.67
    asu
    -0.66
     wildcard
    -0.65
    搜索
    -0.65
     mord
    -0.64
     morg
    -0.64
    SSC
    -0.64
     عک
    -0.64
    POSITIVE LOGITS
     đa
    0.72
     souvent
    0.69
    sect
    0.68
    low
    0.67
     صوت
    0.67
    stg
    0.63
    گذار
    0.63
     DriverManager
    0.63
    hető
    0.62
    로운
    0.62
    Activations Density 0.072%

    No Known Activations