© 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. 16114
    Prev
    Next
    INDEX
    Explanations

    WHAT IS

    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
    ͻ
    -1.53
     inégal
    -1.27
     végétal
    -1.23
    Ꮋ
    -1.19
    욤
    -1.19
    ℞
    -1.18
     énon
    -1.16
     parfois
    -1.15
    cheap
    -1.13
    ējās
    -1.13
    POSITIVE LOGITS
     now
    1.35
     not
    1.30
     another
    1.27
     those
    1.21
     all
    1.20
     meint
    1.20
     children
    1.17
     they
    1.13
     one
    1.12
     long
    1.10
    Activations Density 0.010%

    No Known Activations