© 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. 723
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems and rules

    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
    蠍
    -1.35
    ⬎
    -1.33
    ledad
    -1.33
    irée
    -1.30
     wrze
    -1.30
     noong
    -1.28
    signia
    -1.27
    🅂
    -1.26
    cress
    -1.26
    orghini
    -1.26
    POSITIVE LOGITS
    </em>
    1.54
    But
    1.48
    With
    1.37
    Those
    1.33
    Not
    1.32
    If
    1.31
    コスパ
    1.30
     those
    1.29
     if
    1.26
    And
    1.26
    Activations Density 0.045%

    No Known Activations