© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48648
    Prev
    Next
    INDEX
    Explanations

    tiny house and limitations

    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_16_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
    lords
    0.74
     heterozygous
    0.67
    俎
    0.67
     EtOAc
    0.66
     destinat
    0.66
    deformation
    0.65
    лон
    0.64
     CLOS
    0.64
     dete
    0.62
    lains
    0.62
    POSITIVE LOGITS
     ك
    0.81
     كار
    0.65
     কার
    0.63
    s
    0.61
     werden
    0.60
    b
    0.60
    后
    0.59
    ania
    0.59
    ή
    0.59
    oder
    0.58
    Activations Density 0.000%

    No Known Activations