© 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. 103414
    Prev
    Next
    INDEX
    Explanations

    adjacent places and things

    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
    </h3>
    -3.06
    "
    -2.77
     remplacé
    -2.77
     selben
    -2.63
     If
    -2.61
    место
    -2.30
     We
    -2.28
    ной
    -2.25
     โดย
    -2.19
    новь
    -2.19
    POSITIVE LOGITS
    絎
    3.03
    鯪
    3.00
     så
    2.86
     '
    2.84
    ῞
    2.77
    なので
    2.55
    說
    2.52
    埽
    2.50
     個室
    2.50
    ers
    2.50
    Activations Density 0.016%

    No Known Activations