© 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. 40-GEMMASCOPE-2-RES-65K
    7. 55195
    Prev
    Next
    INDEX
    Explanations

    challenge

    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_40_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
     łat
    0.51
     چ
    0.50
     ch
    0.49
     Chí
    0.47
     trabalh
    0.47
     egyszerű
    0.47
     swiftly
    0.45
     egyéb
    0.45
    Przypisy
    0.44
    다
    0.44
    POSITIVE LOGITS
    is
    0.55
     posed
    0.54
    al
    0.50
    r
    0.50
    b
    0.49
    ポジ
    0.49
    ู
    0.47
    i
    0.46
    l
    0.46
     pose
    0.45
    Activations Density 0.039%

    No Known Activations