© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112023
    Prev
    Next
    INDEX
    Explanations

    really, then

    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
     and
    -1.84
     AGAIN
    -1.65
     or
    -1.59
     algunas
    -1.59
     Makes
    -1.51
     &
    -1.45
     sejumlah
    -1.40
     on
    -1.40
     finalmente
    -1.38
    곽
    -1.38
    POSITIVE LOGITS
     électron
    1.54
    ong
    1.43
     emporter
    1.40
    一个小
    1.38
     любой
    1.38
     courir
    1.38
     inoxydable
    1.35
    ot
    1.35
    を作り
    1.35
     menschlichen
    1.34
    Activations Density 0.010%

    No Known Activations