© 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. 127780
    Prev
    Next
    INDEX
    Explanations

    expressing uncertainty or lack of clarity

    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
    ᚔ
    -2.61
    
    -2.47
    訁
    -2.45
    好きです
    -2.41
    ㉓
    -2.39
    氿
    -2.38
    鹋
    -2.38
    臆
    -2.36
    indelijk
    -2.30
    ⩖
    -2.28
    POSITIVE LOGITS
    .
    3.81
    t
    3.25
    en
    3.17
    or
    3.16
    un
    3.14
    “
    2.81
    on
    2.80
    us
    2.77
    ly
    2.67
    im
    2.63
    Activations Density 0.004%

    No Known Activations