© 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. 34-GEMMASCOPE-RES-131K
    7. 35015
    Prev
    Next
    INDEX
    Explanations

    words ending in 'to'

    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_34/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
     unwanted
    -0.90
     Latter
    -0.86
    utz
    -0.82
     ]}
    -0.79
    setattr
    -0.78
    argon
    -0.78
    IGR
    -0.72
     notable
    -0.72
    nt
    -0.70
     wiem
    -0.70
    POSITIVE LOGITS
    ixar
    0.83
     signora
    0.81
     influen
    0.80
     Tento
    0.79
    serie
    0.79
     proced
    0.78
    retim
    0.78
     Antibodies
    0.77
    czyć
    0.77
     несколько
    0.77
    Activations Density 0.079%

    No Known Activations