© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86857
    Prev
    Next
    INDEX
    Explanations

    golf championship, critique, structure, file, asm

    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
     of
    -1.55
     idag
    -1.39
     erns
    -1.38
     appels
    -1.35
     klasse
    -1.35
    既然
    -1.33
    他
    -1.31
     lakini
    -1.27
    íše
    -1.27
    จาก
    -1.26
    POSITIVE LOGITS
     there
    2.14
    There
    1.95
    When
    1.81
    しちゃ
    1.71
     it
    1.68
     when
    1.67
    It
    1.60
    ご理解
    1.59
    These
    1.55
    Why
    1.53
    Activations Density 0.166%

    No Known Activations