© 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. 109781
    Prev
    Next
    INDEX
    Explanations

    visiting places or people

    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
     locating
    -1.28
    神
    -1.21
     haupts
    -1.20
     vigente
    -1.17
     variedade
    -1.16
    zhong
    -1.09
    それも
    -1.08
     existentes
    -1.06
    ean
    -1.06
     elevados
    -1.05
    POSITIVE LOGITS
     and
    1.59
     with
    1.47
     during
    1.37
     for
    1.33
    During
    1.27
     selama
    1.27
     relatives
    1.27
     untuk
    1.23
     or
    1.21
     sites
    1.21
    Activations Density 0.015%

    No Known Activations