© 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. 10-GEMMASCOPE-RES-131K
    4. 733
    Prev
    Next
    INDEX
    Explanations

    leaves, remaining, only

    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_10/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
     its
    -1.54
     a
    -1.48
     already
    -1.43
     both
    -1.39
     because
    -1.39
    蝎
    -1.31
    ."
    -1.30
     while
    -1.30
     whether
    -1.27
     these
    -1.25
    POSITIVE LOGITS
    gesamt
    1.30
     geniales
    1.25
    ???:
    1.22
     Сколько
    1.17
    其他
    1.16
     navideños
    1.16
    remaining
    1.15
     БО
    1.15
     to
    1.15
     Какой
    1.13
    Activations Density 0.025%

    No Known Activations