© 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. 64999
    Prev
    Next
    INDEX
    Explanations

    qualifiers and descriptors

    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
    殽
    -1.50
     rád
    -1.43
     zaterdag
    -1.41
     prêtre
    -1.41
    傒
    -1.41
     vrijdag
    -1.38
     artikelen
    -1.36
    隳
    -1.35
     juſ
    -1.32
    ísmo
    -1.31
    POSITIVE LOGITS
    y
    1.28
     and
    1.24
    there
    1.17
    r
    1.13
    p
    1.12
    M
    1.11
    k
    1.11
    B
    1.09
    l
    1.08
    L
    1.07
    Activations Density 0.177%

    No Known Activations