© 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. 33436
    Prev
    Next
    INDEX
    Explanations

    single letters in code

    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
     altijd
    -1.19
     всегда
    -1.13
    ţiei
    -1.07
    ₍
    -1.03
     selalu
    -1.02
    Werdegang
    -1.02
     kancel
    -1.00
     sebelum
    -0.96
     voetballer
    -0.96
    焱
    -0.96
    POSITIVE LOGITS
     capable
    1.09
     like
    1.05
     need
    1.01
     was
    0.95
    '
    0.94
    rédients
    0.94
     able
    0.90
    𝒚
    0.88
     thì
    0.88
     distinguished
    0.88
    Activations Density 0.003%

    No Known Activations