© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50595
    Prev
    Next
    INDEX
    Explanations

    often has, worried about, Earth Conspiracy

    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_65k_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
    鏁
    0.51
    prac
    0.46
    getCode
    0.45
     actuated
    0.44
     quarry
    0.44
    ческие
    0.42
    ský
    0.42
    断面
    0.42
    lymph
    0.41
     நோக்க
    0.41
    POSITIVE LOGITS
     inklusive
    0.51
    亽
    0.47
     representante
    0.47
     olisi
    0.46
     negatif
    0.46
     colabor
    0.45
     komment
    0.45
     supervis
    0.45
     estudiante
    0.45
     obviamente
    0.45
    Activations Density 0.019%

    No Known Activations