© 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. 34-GEMMASCOPE-RES-131K
    7. 49446
    Prev
    Next
    INDEX
    Explanations

    numbers and surrounding characters

    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
    čních
    -0.86
    ὸς
    -0.84
     ROBER
    -0.74
     mộc
    -0.73
     Mahoney
    -0.72
    맞
    -0.72
    żdż
    -0.72
    arakhand
    -0.72
    يل
    -0.71
     Mujer
    -0.71
    POSITIVE LOGITS
    hnung
    0.85
     데
    0.82
    particularly
    0.77
     but
    0.76
     particuli
    0.76
    cled
    0.76
    othermal
    0.76
    #:
    0.76
    Bekijk
    0.75
     rewatch
    0.75
    Activations Density 0.014%

    No Known Activations