© 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. 34-GEMMASCOPE-RES-131K
    7. 77350
    Prev
    Next
    INDEX
    Explanations

    return value or inspect

    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
     Quaker
    -0.92
     lifter
    -0.89
    ጎ
    -0.81
    ApiKey
    -0.81
     yoghurt
    -0.77
     jogger
    -0.77
     semaines
    -0.77
    жного
    -0.75
     clout
    -0.75
    继承
    -0.75
    POSITIVE LOGITS
    newVal
    0.96
    .].
    0.78
    حيات
    0.78
    ):-
    0.77
     ندار
    0.77
    このように
    0.77
    éco
    0.76
    ํ
    0.76
     örgü
    0.73
     interruptions
    0.72
    Activations Density 0.063%

    No Known Activations