© 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. 78838
    Prev
    Next
    INDEX
    Explanations

    don't really care

    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
    basically
    -1.46
     rám
    -1.42
     fotografi
    -1.41
     deklar
    -1.40
     perspek
    -1.39
     désert
    -1.38
     incrí
    -1.35
     aspek
    -1.34
    slightly
    -1.33
    relatively
    -1.33
    POSITIVE LOGITS
     ‘
    1.41
     “
    1.34
     sure
    1.33
     any
    1.31
     new
    1.28
    K
    1.23
    ‘
    1.22
    t
    1.20
     know
    1.19
    ”
    1.19
    Activations Density 0.032%

    No Known Activations