© 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. 214828
    Prev
    Next
    INDEX
    Explanations

    how things work

    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
    aba
    0.41
    begin
    0.40
    簟
    0.40
    end
    0.40
    Twilight
    0.39
    7
    0.38
    affles
    0.38
    4
    0.38
    3
    0.37
     seemed
    0.37
    POSITIVE LOGITS
     répét
    0.42
     تُ
    0.42
    🥲
    0.42
     ORIGINAL
    0.41
     അഭി
    0.41
    했
    0.40
    стро
    0.39
     оригі
    0.39
    KeepOriginal
    0.39
     caer
    0.38
    Activations Density 0.001%

    No Known Activations