© 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. 64883
    Prev
    Next
    INDEX
    Explanations

    known with

    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
     only
    -1.34
    tallet
    -1.11
    máscara
    -1.02
    ಇ
    -1.02
     июня
    -1.02
     bereits
    -1.02
     an
    -1.00
     use
    -1.00
     two
    -0.98
     citoyens
    -0.96
    POSITIVE LOGITS
     [
    2.03
     my
    1.32
     (
    1.28
     we
    1.27
     our
    1.26
     myself
    1.20
     I
    1.03
     guys
    1.02
     sentimentos
    0.99
     encyclo
    0.98
    Activations Density 0.014%

    No Known Activations