© 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. 22-GEMMASCOPE-RES-131K
    7. 73234
    Prev
    Next
    INDEX
    Explanations

    web URLs and names

    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_22/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
    しましたが
    -1.12
     variously
    -1.06
    a
    -1.05
    ایا
    -1.04
     illustrate
    -1.04
    举例
    -1.01
    koala
    -1.00
     여러
    -1.00
     mehrere
    -0.99
    一系列
    -0.98
    POSITIVE LOGITS
    _
    1.40
    ://
    1.29
    @
    1.28
    ographer
    1.24
     menik
    1.22
    0
    1.20
    頜
    1.19
    готовки
    1.16
    йки
    1.16
    lifier
    1.13
    Activations Density 0.151%

    No Known Activations