© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144496
    Prev
    Next
    INDEX
    Explanations

    plant profiles, care label, local game, psychic consciousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ZE
    0.47
    Roma
    0.47
     perverse
    0.45
    殺
    0.43
     mele
    0.43
     sopra
    0.43
     mulheres
    0.43
     sepsis
    0.43
    ズ
    0.43
    дето
    0.42
    POSITIVE LOGITS
    bark
    0.47
    itian
    0.43
    orsement
    0.43
     Chalk
    0.42
    특별시
    0.42
    负责
    0.42
    <0x8A>
    0.41
    icio
    0.41
    quirer
    0.41
    plotlib
    0.40
    Activations Density 0.006%

    No Known Activations