© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39086
    Prev
    Next
    INDEX
    Explanations

    Víctor, space, LOAD, CD, What, IR, Can

    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
    t
    -3.77
    ⼥
    -2.45
    莧
    -2.41
    NOSIS
    -2.22
    PARATION
    -2.20
    哢
    -2.19
     概要
    -2.13
    т
    -2.09
     arrivato
    -2.08
    να
    -2.06
    POSITIVE LOGITS
    </strong>
    3.52
    </h3>
    3.08
     \
    2.36
     
    2.17
    该公司
    2.17
    &#
    2.08
    ’
    2.08
     same
    2.08
     outgoing
    2.06
    ‘
    2.03
    Activations Density 0.000%

    No Known Activations