© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3746
    Prev
    Next
    INDEX
    Explanations

    from the start

    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
     also
    -2.09
     también
    -1.55
     também
    -1.51
     również
    -1.37
     only
    -1.37
     ALSO
    -1.34
     גם
    -1.28
     тоже
    -1.20
     також
    -1.19
    simpan
    -1.16
    POSITIVE LOGITS
    neling
    1.55
     to
    1.52
     }],
    1.51
     sejak
    1.31
    which
    1.29
    hamel
    1.25
    rowable
    1.25
    那人
    1.23
    that
    1.22
    The
    1.20
    Activations Density 0.047%

    No Known Activations