© 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. 87297
    Prev
    Next
    INDEX
    Explanations

    jsfiddle links

    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
     debugger
    -0.73
     resor
    -0.71
    四十
    -0.69
     modified
    -0.68
     qualifies
    -0.68
     Reservoir
    -0.66
    adona
    -0.66
     Auxiliary
    -0.66
     reserv
    -0.66
    Reserv
    -0.65
    POSITIVE LOGITS
     Blau
    0.71
    ॥
    0.69
    loadAll
    0.69
     teknik
    0.68
     اگه
    0.68
    Intl
    0.66
    Lorem
    0.66
    Elev
    0.66
     kony
    0.65
    っていく
    0.65
    Activations Density 0.058%

    No Known Activations