© 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. 34-GEMMASCOPE-RES-131K
    7. 99684
    Prev
    Next
    INDEX
    Explanations

    occupations and roles

    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
     Unterscheidung
    -1.21
    somewhat
    -1.16
    さまざま
    -1.16
     hôtels
    -1.15
     enorme
    -1.13
    larg
    -1.11
    様々
    -1.10
    slightly
    -1.09
    olving
    -1.08
    beginning
    -1.08
    POSITIVE LOGITS
     who
    1.49
     of
    1.47
     says
    1.38
     wants
    1.38
     had
    1.31
     asked
    1.29
     said
    1.26
     having
    1.24
     gave
    1.23
     wanted
    1.20
    Activations Density 0.105%

    No Known Activations