© 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. 74274
    Prev
    Next
    INDEX
    Explanations

    have to do/say/go

    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
    lls
    -1.84
    赑
    -1.84
    0
    -1.66
     comunica
    -1.63
     domina
    -1.58
        
    -1.58
    ﮦ
    -1.58
    itados
    -1.56
    饃
    -1.56
    饹
    -1.55
    POSITIVE LOGITS
     those
    1.71
     that
    1.70
     this
    1.66
     of
    1.64
    edere
    1.59
     teilweise
    1.57
     türlü
    1.54
    などを
    1.52
     it
    1.51
    and
    1.48
    Activations Density 0.033%

    No Known Activations