© 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. 73120
    Prev
    Next
    INDEX
    Explanations

    type casting and conversion

    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
    shades
    -1.20
     düşünü
    -1.13
     ſuch
    -1.13
    sterious
    -1.11
     cabra
    -1.05
     Probably
    -1.05
    嗐
    -1.03
    ığını
    -1.02
    inerario
    -1.02
    mayın
    -1.02
    POSITIVE LOGITS
     of
    1.76
    ou
    1.39
    but
    1.31
    en
    1.22
    an
    1.19
    你了
    1.10
     это
    1.03
    is
    1.03
    we
    1.02
    ens
    1.00
    Activations Density 0.004%

    No Known Activations