© 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. 110499
    Prev
    Next
    INDEX
    Explanations

    Indian state or US state

    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
     scoperto
    -0.86
     uovo
    -0.79
     rapat
    -0.78
     détru
    -0.78
     olho
    -0.78
     FOLLOWING
    -0.76
    ฀
    -0.76
    gebäude
    -0.74
    报记者
    -0.74
     Projet
    -0.73
    POSITIVE LOGITS
     createState
    1.65
     state
    1.56
     State
    1.26
    PageState
    1.18
    outState
    1.15
    state
    1.13
     states
    1.11
    State
    1.08
     STATE
    1.02
    STATE
    1.02
    Activations Density 0.002%

    No Known Activations