© 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. 109582
    Prev
    Next
    INDEX
    Explanations

    succulent plants and lichens

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

    scientific or technical descriptions of species and organisms.

    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
    vák
    -0.73
    rali
    -0.73
     Power
    -0.71
     飞
    -0.71
     Bürger
    -0.70
    mdl
    -0.69
    IBRATION
    -0.68
    انيه
    -0.68
    dige
    -0.67
    万美元
    -0.66
    POSITIVE LOGITS
     succulent
    1.18
     succulents
    1.13
     miniature
    0.86
     rock
    0.86
    tiny
    0.83
     rosette
    0.81
     drought
    0.80
    hens
    0.79
    Sed
    0.79
    phazard
    0.79
    Activations Density 0.018%

    No Known Activations