© 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. 21121
    Prev
    Next
    INDEX
    Explanations

    gain access, information, or insight

    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
     “
    -2.69
    0
    -2.48
     finding
    -2.23
     Это
    -2.14
     ~
    -2.08
     Then
    -2.08
     Konferenz
    -2.06
    娘娘
    -1.98
     lofty
    -1.92
    Mhz
    -1.91
    POSITIVE LOGITS
    ኧ
    2.83
    犼
    2.70
    genodigd
    2.61
    螓
    2.58
    ଝ
    2.55
    穑
    2.52
    geſ
    2.44
     花纹
    2.39
    AdvEx
    2.36
    鼇
    2.31
    Activations Density 0.007%

    No Known Activations