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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66929
    Prev
    Next
    INDEX
    Explanations

    collaborators and commentators

    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
    When
    -2.92
    Every
    -2.70
    Some
    -2.69
    ЛИ
    -2.47
    Each
    -2.44
    able
    -2.44
    裡的
    -2.39
    Those
    -2.36
    可
    -2.34
     konsep
    -2.33
    POSITIVE LOGITS
     was
    3.55
    雠
    3.22
    酲
    2.91
    
    2.80
     and
    2.69
    籴
    2.66
     manter
    2.63
    ⏑
    2.58
     We
    2.56
    鸲
    2.55
    Activations Density 0.008%

    No Known Activations