© 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. 15789
    Prev
    Next
    INDEX
    Explanations

    Audacity, Lemma, GB_red

    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
     tako
    -0.94
     very
    -0.92
     olas
    -0.90
     Logement
    -0.89
     templo
    -0.88
     considera
    -0.84
     cór
    -0.84
     установ
    -0.82
     hijo
    -0.82
     balcón
    -0.82
    POSITIVE LOGITS
    ὴν
    1.14
    Ils
    1.01
    ณฑ
    0.98
    ⴻ
    0.98
     새로운
    0.98
     esteja
    0.96
     KCl
    0.96
     precisamos
    0.95
    iglie
    0.94
     Mammoth
    0.94
    Activations Density 0.002%

    No Known Activations