© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11342
    Prev
    Next
    INDEX
    Explanations

    specific entity identification

    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_22/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
    ,
    -1.16
     девя
    -1.12
     acht
    -1.05
    璟
    -1.05
    umerable
    -1.05
     baden
    -1.05
     heilig
    -1.04
     heilige
    -1.04
    composed
    -1.03
    average
    -1.02
    POSITIVE LOGITS
     already
    1.43
     bereits
    1.38
     уже
    1.25
     your
    1.22
     indicated
    1.20
     previously
    1.20
     appropriate
    1.17
     same
    1.16
     existing
    1.13
    既に
    1.09
    Activations Density 0.081%

    No Known Activations