© 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. 117096
    Prev
    Next
    INDEX
    Explanations

    listing included items

    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
    容器
    -0.87
     is
    -0.82
     છે
    -0.81
    addContainer
    -0.78
     dago
    -0.77
    }:=\
    -0.77
    maksi
    -0.76
    moed
    -0.75
    Antwoord
    -0.74
    壮
    -0.73
    POSITIVE LOGITS
     included
    6.13
    included
    4.72
     Included
    4.44
    Included
    4.34
     INCLUDED
    3.73
     ranged
    3.00
     incluido
    2.97
     include
    2.94
     consisted
    2.89
    INCLUDED
    2.81
    Activations Density 0.134%

    No Known Activations