© 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. 33350
    Prev
    Next
    INDEX
    Explanations

    end of day/stage

    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
     because
    -1.23
    بعاد
    -1.16
     waarop
    -1.14
    をする
    -1.13
     rádio
    -1.12
    Pengertian
    -1.11
     that
    -1.11
     trá
    -1.10
    astră
    -1.10
     teclas
    -1.09
    POSITIVE LOGITS
    g
    1.32
    j
    1.27
    p
    1.27
    v
    1.27
    m
    1.26
    un
    1.18
    d
    1.14
     «
    1.14
    f
    1.13
    z
    1.12
    Activations Density 0.081%

    No Known Activations