© 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. 10-GEMMASCOPE-RES-131K
    7. 84361
    Prev
    Next
    INDEX
    Explanations

    being, taking, finding, generating

    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_10/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
     there
    -1.63
    ll
    -1.23
    There
    -1.22
     apreciar
    -1.20
     here
    -1.19
     manner
    -1.18
     this
    -1.17
    ?
    -1.14
     efectuar
    -1.13
    leriyle
    -1.12
    POSITIVE LOGITS
    diese
    1.48
    ๘
    1.38
    Diese
    1.30
     ujar
    1.26
     ་
    1.23
    ohne
    1.23
    itiert
    1.22
    częściej
    1.22
     czerwca
    1.20
    税込
    1.19
    Activations Density 0.110%

    No Known Activations