© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14083
    Prev
    Next
    INDEX
    Explanations

    when followed by we or the

    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
    μων
    -1.34
    ᾿
    -1.32
    ּוֹ
    -1.31
    וּ
    -1.25
     avenir
    -1.21
     salvation
    -1.18
    ᅲ
    -1.17
     TÉ
    -1.16
     répand
    -1.14
     fazia
    -1.14
    POSITIVE LOGITS
     or
    1.45
     others
    1.26
     those
    1.23
     people
    1.20
     it
    1.20
     parts
    1.19
     what
    1.17
    也
    1.16
    去
    1.15
     our
    1.13
    Activations Density 0.053%

    No Known Activations