© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76352
    Prev
    Next
    INDEX
    Explanations

    valid question

    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_34/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
    ということを
    -1.38
    なんだろう
    -1.37
    かも知
    -1.31
     valsty
    -1.27
    に於
    -1.25
    なのかな
    -1.16
     великолеп
    -1.14
    ということは
    -1.13
    escalier
    -1.13
    lecteur
    -1.12
    POSITIVE LOGITS
    子は
    1.70
    子が
    1.55
    子さん
    1.45
    日から
    1.44
    anyahu
    1.37
    次回は
    1.33
     его
    1.32
    (^^)
    1.28
    日は
    1.28
    ?
    1.23
    Activations Density 0.003%

    No Known Activations