© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30779
    Prev
    Next
    INDEX
    Explanations

    HT or HT-

    np_acts-logits-general · gemini-2.5-flash-lite

    cell line identifiers starting with "HT" followed by numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    anima
    -0.80
    Apre
    -0.74
     العد
    -0.73
    ウンジ
    -0.72
    Avg
    -0.70
    Mek
    -0.70
    ukin
    -0.69
     lokale
    -0.69
    Univ
    -0.69
    apartment
    -0.68
    POSITIVE LOGITS
    wasser
    0.84
     HT
    0.82
     deseo
    0.73
     Beginn
    0.73
     см
    0.73
     hatte
    0.72
    ッキー
    0.71
     drums
    0.71
    pagnol
    0.71
    ведена
    0.70
    Activations Density 0.032%

    No Known Activations