© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109915
    Prev
    Next
    INDEX
    Explanations

    offers and provides

    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
    ÓW
    -1.19
     berkomunikasi
    -1.13
     dormitorios
    -1.11
    нциклопе
    -1.10
     بودند
    -1.09
     باید
    -1.09
    nsylvania
    -1.08
    になってしまう
    -1.08
     sienten
    -1.03
    越多
    -1.03
    POSITIVE LOGITS
     offer
    2.03
     offers
    1.91
     provide
    1.75
     is
    1.66
     offering
    1.66
     has
    1.63
     help
    1.60
     promise
    1.55
     provides
    1.53
     also
    1.48
    Activations Density 0.034%

    No Known Activations