© 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. 112873
    Prev
    Next
    INDEX
    Explanations

    directed to us

    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
    淠
    -2.41
     ſy
    -1.92
    ſſi
    -1.88
    鹪
    -1.86
    ༵
    -1.86
    鸶
    -1.85
     atracción
    -1.80
    鸸
    -1.78
    蕺
    -1.78
    砗
    -1.78
    POSITIVE LOGITS
    j
    2.66
    s
    2.31
    p
    2.30
    u
    2.20
    c
    2.19
    </h3>
    2.11
    f
    2.11
    b
    2.08
    "
    1.98
    l
    1.93
    Activations Density 0.028%

    No Known Activations