© 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. 3797
    Prev
    Next
    INDEX
    Explanations

    contrast or caveat after comma

    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
    inuous
    0.43
    Confusion
    0.43
    ξης
    0.42
     zodat
    0.42
    !.
    0.41
     denn
    0.41
     такая
    0.41
    損
    0.40
     poils
    0.40
    ज्ञापन
    0.40
    POSITIVE LOGITS
     crucially
    0.71
     importantly
    0.71
     unfortunately
    0.62
     unsurprisingly
    0.59
     according
    0.56
     ultimately
    0.54
     경우
    0.53
     additionally
    0.51
     conversely
    0.51
     hopefully
    0.50
    Activations Density 0.114%

    No Known Activations