© 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. 25824
    Prev
    Next
    INDEX
    Explanations

    telescope and its parts

    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
    鏽
    -0.82
     autopilot
    -0.72
     Amtrak
    -0.70
    ดด
    -0.70
    adé
    -0.70
     intorno
    -0.69
    teri
    -0.69
     armour
    -0.67
    ggy
    -0.66
     beards
    -0.66
    POSITIVE LOGITS
     telescope
    1.77
     telescopes
    1.48
    teles
    1.30
     teles
    1.22
     Telescope
    1.19
     теле
    1.14
     Teles
    1.14
     mirror
    1.02
    Mirror
    1.01
    mirror
    0.96
    Activations Density 0.030%

    No Known Activations