© 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. 59491
    Prev
    Next
    INDEX
    Explanations

    magnetic tape recorder

    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
    hika
    -0.88
    рна
    -0.79
    olingo
    -0.76
    }~
    -0.76
    oglo
    -0.76
     Javier
    -0.75
    längerung
    -0.75
     cytok
    -0.71
    pgf
    -0.70
    <0x9A>
    -0.70
    POSITIVE LOGITS
     tape
    2.08
     reel
    1.95
     Tape
    1.70
     tapes
    1.63
    Tape
    1.59
     reels
    1.57
    tape
    1.56
     Reel
    1.47
     cassette
    1.47
    reel
    1.33
    Activations Density 0.059%

    No Known Activations