© 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. 31-GEMMASCOPE-2-RES-65K
    7. 55207
    Prev
    Next
    INDEX
    Explanations

    calculating quantities

    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
    保安
    0.44
     оттен
    0.41
    attled
    0.38
    λλά
    0.38
    ανά
    0.36
    否则
    0.35
    ယ
    0.35
    atters
    0.35
     многи
    0.35
    **/
    0.35
    POSITIVE LOGITS
     multiplied
    0.42
     alz
    0.42
     actif
    0.42
     คูณ
    0.42
     eluted
    0.41
     passive
    0.40
     deposition
    0.40
     SBI
    0.40
     drift
    0.40
     exon
    0.40
    Activations Density 0.002%

    No Known Activations