© 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. 39358
    Prev
    Next
    INDEX
    Explanations

    higher than

    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
    ጴ
    -1.76
     necessari
    -1.63
    sekten
    -1.62
     VET
    -1.58
    
    -1.55
    rots
    -1.55
    ⽼
    -1.52
     $*$
    -1.52
    rivial
    -1.52
    auge
    -1.48
    POSITIVE LOGITS
     an
    1.59
    A
    1.59
    ),
    1.55
     last
    1.51
     after
    1.49
    ”.
    1.45
     delivering
    1.45
     leur
    1.40
    The
    1.38
     maximum
    1.38
    Activations Density 0.256%

    No Known Activations