© 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. 11507
    Prev
    Next
    INDEX
    Explanations

    fashions, authors, stage, catwalk

    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
     acogedor
    -1.16
     is
    -1.15
     hermosas
    -1.05
    feuille
    -1.01
     sonrası
    -1.01
     kiedy
    -0.99
     situation
    -0.98
     DAYS
    -0.98
     always
    -0.97
     disponibilidad
    -0.97
    POSITIVE LOGITS
     Thursday
    1.13
    alarme
    1.13
     of
    1.04
     république
    0.98
    参加
    0.98
     fasse
    0.98
     erstmals
    0.96
     themselves
    0.95
    無印
    0.95
     jugu
    0.94
    Activations Density 0.084%

    No Known Activations