© 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-262K
    7. 21112
    Prev
    Next
    INDEX
    Explanations

    service requests

    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
    ks
    0.55
    leur
    0.47
     』
    0.45
    lov
    0.43
    clusive
    0.42
    뀝
    0.42
    មិន
    0.42
    лькі
    0.41
    緘
    0.41
    種類
    0.40
    POSITIVE LOGITS
     aeron
    0.54
     parecer
    0.50
     suscept
    0.44
     tubig
    0.44
     trai
    0.44
     banyak
    0.43
     volleyball
    0.43
    ସ
    0.43
     conden
    0.43
     صحت
    0.43
    Activations Density 0.006%

    No Known Activations