© 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-262K
    7. 12500
    Prev
    Next
    INDEX
    Explanations

    containing "ant" or "ent"

    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_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
    ět
    0.51
    ங்குக
    0.44
    Џ
    0.44
    ัติ
    0.43
    었는데
    0.43
    haut
    0.41
    으로
    0.40
    ترل
    0.40
    atasi
    0.39
    たい
    0.39
    POSITIVE LOGITS
    inental
    0.54
    inued
    0.47
    yfik
    0.44
    )}.
    0.43
    rifugal
    0.43
    र्गत
    0.43
    heses
    0.43
     vente
    0.42
    anglement
    0.42
    hetical
    0.42
    Activations Density 0.053%

    No Known Activations