© 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. 118150
    Prev
    Next
    INDEX
    Explanations

    VHS and cassette tape formats

    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
     disc
    -1.11
    Disc
    -1.05
     Disc
    -1.01
    disc
    -0.91
     disk
    -0.86
     discs
    -0.86
     Kindle
    -0.82
    Kindle
    -0.78
     Disk
    -0.75
    disk
    -0.74
    POSITIVE LOGITS
     tape
    3.23
     tapes
    2.91
     Tape
    2.58
    tape
    2.58
     cassette
    2.56
    Tape
    2.41
     cassettes
    2.25
     VHS
    2.14
    tapes
    2.11
    テープ
    2.06
    Activations Density 0.057%

    No Known Activations