Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 9102
    Prev
    Next
    INDEX
    Explanations

    encourages or invites action

    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
     obwohl
    -1.17
     céramique
    -1.13
    orithms
    -1.13
     possibilité
    -1.06
    nera
    -1.06
     plainte
    -1.04
     nonostante
    -1.02
     împreună
    -1.02
    致力于
    -1.02
     搭
    -1.02
    POSITIVE LOGITS
     us
    2.19
     them
    2.05
     him
    1.80
     others
    1.71
     everyone
    1.47
     participation
    1.47
     anyone
    1.33
    others
    1.30
     people
    1.20
     and
    1.18
    Activations Density 0.049%

    No Known Activations