© 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. 73371
    Prev
    Next
    INDEX
    Explanations

    2. Description of the Related Art

    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
    —
    -1.55
     is
    -1.34
    this
    -1.23
    '
    -1.23
    es
    -1.23
    ors
    -1.21
    *****
    -1.19
    an
    -1.18
    al
    -1.17
    se
    -1.17
    POSITIVE LOGITS
     organizador
    1.36
    Primero
    1.32
     condicionado
    1.32
     distribuidor
    1.27
     its
    1.27
     encantador
    1.27
    şek
    1.26
    はじめまして
    1.24
     ladr
    1.21
    でしたか
    1.20
    Activations Density 0.008%

    No Known Activations