© 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. 10-GEMMASCOPE-RES-131K
    7. 43103
    Prev
    Next
    INDEX
    Explanations

    map locator information calculator

    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_10/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
    Một
    -1.30
    ßig
    -1.27
     ‘
    -1.27
    Ḡ
    -1.26
    ]
    -1.22
     Utiliza
    -1.21
     genug
    -1.20
    ">
    -1.16
    )
    -1.14
     primeras
    -1.14
    POSITIVE LOGITS
     how
    1.26
     their
    1.21
     our
    1.14
     decisão
    1.13
     any
    1.12
    癭
    1.12
    部分を
    1.10
     boute
    1.09
     anyone
    1.09
     rocher
    1.08
    Activations Density 0.166%

    No Known Activations