© 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. 22-GEMMASCOPE-RES-131K
    7. 12182
    Prev
    Next
    INDEX
    Explanations

    `PED` followed by verbs

    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
    kond
    -1.44
    dekor
    -1.36
     kosme
    -1.30
     kommunik
    -1.30
     japonesa
    -1.30
    ₁(
    -1.27
    kritik
    -1.27
     desfile
    -1.24
     Kamera
    -1.22
    сама
    -1.21
    POSITIVE LOGITS
     –
    1.49
    v
    1.39
    u
    1.31
    ものが
    1.29
    en
    1.27
    on
    1.25
    yn
    1.23
    F
    1.23
    E
    1.20
    j
    1.20
    Activations Density 0.002%

    No Known Activations