© 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. 12285
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
     of
    -1.42
     Bildungs
    -1.27
     also
    -1.24
     from
    -1.09
     aka
    -1.07
    through
    -1.02
     utilized
    -1.00
    high
    -0.99
     resa
    -0.98
     deines
    -0.98
    POSITIVE LOGITS
    ına
    1.13
     repuesto
    1.10
     metoda
    1.08
     magnétique
    1.06
     Öz
    1.05
     rencontr
    1.05
     libido
    1.02
    studie
    1.01
    ığı
    1.00
     dekol
    1.00
    Activations Density 0.161%

    No Known Activations