© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118864
    Prev
    Next
    INDEX
    Explanations

    100% followed by a word

    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
     trám
    -1.13
     avancer
    -1.07
    THERS
    -1.04
     presque
    -1.02
     exempl
    -1.00
    铪
    -0.99
    だいぶ
    -0.97
    鸝
    -0.97
     padrão
    -0.97
     largely
    -0.97
    POSITIVE LOGITS
     pure
    1.28
     Australian
    1.27
     what
    1.21
     Pure
    1.09
     satisfaction
    1.07
     on
    1.05
     American
    1.01
     natural
    1.01
     percent
    1.01
     Canadian
    1.00
    Activations Density 0.010%

    No Known Activations