© 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. 10-GEMMASCOPE-RES-131K
    7. 692
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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
    rivial
    -1.44
    pportun
    -1.43
    ülerin
    -1.41
     puteți
    -1.39
    vgili
    -1.39
    tenor
    -1.38
    VEGF
    -1.38
     Inſ
    -1.37
     pergunta
    -1.36
     geene
    -1.36
    POSITIVE LOGITS
    :
    1.87
     or
    1.79
    -
    1.68
    —
    1.58
    You
    1.58
    They
    1.54
     –
    1.49
    …
    1.49
     they
    1.47
    )
    1.47
    Activations Density 0.595%

    No Known Activations