© 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. 19949
    Prev
    Next
    INDEX
    Explanations

    Perceived support, Narayana Rao

    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
     BorderLayout
    -1.51
    หน้านี้
    -1.38
    toFloat
    -1.34
    setNome
    -1.34
    此事
    -1.33
     Belarusian
    -1.31
    entrale
    -1.27
    luß
    -1.26
    荤
    -1.25
    uaikan
    -1.24
    POSITIVE LOGITS
    }
    2.03
    —
    1.50
    それが
    1.46
    ’
    1.41
     though
    1.38
     utilizada
    1.37
    1.37
    </b>
    1.36
    </sub>
    1.34
     когда
    1.34
    Activations Density 0.002%
    No Known Activations