© 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. 10-GEMMASCOPE-RES-131K
    7. 21176
    Prev
    Next
    INDEX
    Explanations

    special characters indicating context

    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
    There
    -3.83
     superbly
    -3.72
     Usually
    -3.55
     Surprisingly
    -3.53
     cleverly
    -3.52
    Even
    -3.50
     undeniably
    -3.47
     Ironically
    -3.45
    After
    -3.44
    When
    -3.38
    POSITIVE LOGITS
     quintessential
    3.59
     revamped
    3.53
     ridiculously
    3.52
     insanely
    3.52
     luscious
    3.45
     delightfully
    3.41
     overly
    3.39
     dando
    3.39
     astounding
    3.39
    苤
    3.38
    Activations Density 0.032%

    No Known Activations