© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    who followed by verbs

    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
     )
    -1.52
     there
    -1.52
    and
    -1.52
    及び
    -1.46
     và
    -1.45
     उन्हें
    -1.45
     から
    -1.45
    на
    -1.43
     &
    -1.43
    }}
    -1.42
    POSITIVE LOGITS
    幛
    1.86
    ܖ
    1.73
    桖
    1.73
    -“
    1.68
     elek
    1.66
    noStroke
    1.66
    媄
    1.66
    屺
    1.65
    −/−
    1.60
    ’,
    1.59
    Activations Density 0.030%

    No Known Activations