© 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-65K
    7. 35749
    Prev
    Next
    INDEX
    Explanations

    minimizing or reducing or building

    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
    iterranean
    0.41
    ostrum
    0.40
     unquestion
    0.40
     legno
    0.39
     jeweil
    0.39
    toires
    0.38
    𝗹
    0.38
     undisputed
    0.38
    osterone
    0.38
     hyaluronic
    0.38
    POSITIVE LOGITS
    츈
    0.48
     Madness
    0.46
     intram
    0.46
     باشید
    0.46
     invocation
    0.44
     입장
    0.44
    জগ
    0.43
     Compatibility
    0.43
    тся
    0.42
     Concepts
    0.42
    Activations Density 0.011%

    No Known Activations