© 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. 10-GEMMASCOPE-RES-131K
    7. 129740
    Prev
    Next
    INDEX
    Explanations

    starts list item or answer

    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_10/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
    replyreport
    -1.78
    2
    -1.76
    "
    -1.74
    3
    -1.72
     "
    -1.72
    ve
    -1.65
    造成的
    -1.61
    -
    -1.61
     $
    -1.60
    $
    -1.60
    POSITIVE LOGITS
     of
    2.25
     to
    1.63
    zji
    1.59
     abbiamo
    1.48
    nyv
    1.47
    müller
    1.47
    sieve
    1.46
     we
    1.46
     there
    1.44
     on
    1.43
    Activations Density 0.009%

    No Known Activations