© 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. 73620
    Prev
    Next
    INDEX
    Explanations

    getApplication Context

    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
     ideen
    -2.81
    
    -2.55
     risiko
    -2.36
    躄
    -2.28
     verhind
    -2.19
     klarer
    -2.19
     rollen
    -2.17
     geze
    -2.16
     bemer
    -2.13
    」，
    -2.05
    POSITIVE LOGITS
    ’
    3.03
    :”
    2.72
    (“
    2.63
    曏
    2.58
    .”.
    2.45
    ..”
    2.41
    m
    2.41
    凊
    2.28
     gracious
    2.27
    —”
    2.25
    Activations Density 0.000%

    No Known Activations