© 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. 12240
    Prev
    Next
    INDEX
    Explanations

    with producer or collaborator

    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
     other
    -1.12
     when
    -1.05
     Sänger
    -0.93
     otros
    -0.93
     others
    -0.92
     each
    -0.90
    udessa
    -0.86
    PhysRevLett
    -0.84
    zmán
    -0.84
     our
    -0.84
    POSITIVE LOGITS
     nô
    1.19
    Experienced
    1.11
    Aktualisiert
    1.02
     dì
    0.98
     inſ
    0.98
     choisi
    0.98
     chô
    0.98
    enaus
    0.97
    formazioni
    0.96
    vied
    0.96
    Activations Density 0.066%

    No Known Activations