© 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. 34-GEMMASCOPE-RES-131K
    7. 93323
    Prev
    Next
    INDEX
    Explanations

    as ___ as possible

    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
    tache
    -0.84
    Öffnungszeiten
    -0.83
    ръ
    -0.81
     ͡°
    -0.80
    Grüne
    -0.79
    ➴
    -0.79
    PARATUS
    -0.78
    osten
    -0.78
    Vendo
    -0.78
     personnalisée
    -0.77
    POSITIVE LOGITS
     possible
    8.63
    possible
    6.25
    Possible
    5.78
     Possible
    5.56
     possível
    5.16
     возмо
    5.00
     posible
    4.94
     posibles
    4.75
     möglich
    4.66
     mogelijk
    4.59
    Activations Density 0.138%

    No Known Activations