© 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. 10-GEMMASCOPE-RES-131K
    7. 44167
    Prev
    Next
    INDEX
    Explanations

    across the

    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
     “
    -1.39
    which
    -1.30
    )$,
    -1.27
     usando
    -1.26
    />
    -1.25
    櫚
    -1.22
    見えます
    -1.21
    issage
    -1.18
    eapples
    -1.18
    uluş
    -1.17
    POSITIVE LOGITS
     our
    1.45
    bundet
    1.40
     you
    1.37
    Drei
    1.35
     both
    1.34
     BOTH
    1.34
    معلومات
    1.32
    Объем
    1.31
    Sonstiges
    1.30
    ︓
    1.28
    Activations Density 0.063%

    No Known Activations