© 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. 93408
    Prev
    Next
    INDEX
    Explanations

    most, some, many cases

    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
     dejes
    -0.84
    점
    -0.83
     фильме
    -0.83
    MessageOf
    -0.83
    ês
    -0.82
     liksom
    -0.82
    givings
    -0.81
    чня
    -0.81
    ggg
    -0.81
    ₑ
    -0.80
    POSITIVE LOGITS
     cases
    6.22
    cases
    3.92
     case
    3.73
     instances
    3.72
    Cases
    3.58
     Cases
    3.53
     casos
    3.47
     CASES
    2.88
     случаев
    2.80
     gevallen
    2.72
    Activations Density 0.073%

    No Known Activations