© 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. 94137
    Prev
    Next
    INDEX
    Explanations

    object member access

    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
     but
    -1.29
    ｪ
    -1.20
    capai
    -1.17
    Both
    -1.17
    dekat
    -1.12
    ｧ
    -1.10
    $.}
    -1.08
    etero
    -1.05
    unjung
    -1.04
     косме
    -1.04
    POSITIVE LOGITS
     also
    2.02
     همچنین
    1.74
     также
    1.31
    ___________
    1.27
    もある
    1.25
    _________
    1.23
    也没有
    1.22
    んでも
    1.22
    ...............
    1.21
     --->
    1.20
    Activations Density 0.017%

    No Known Activations