© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19715
    Prev
    Next
    INDEX
    Explanations

    "I" followed by a verb

    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
    失敗
    0.46
     א
    0.45
     bất
    0.45
    பர்
    0.44
     خدمات
    0.44
    赤ちゃん
    0.44
     saudara
    0.43
    ायक
    0.43
     கிடைத்தது
    0.43
     microwaves
    0.42
    POSITIVE LOGITS
    do
    0.45
    o
    0.44
    scroll
    0.43
    poque
    0.43
     will
    0.43
    would
    0.43
    to
    0.42
     sería
    0.42
     journey
    0.41
    aré
    0.41
    Activations Density 0.010%

    No Known Activations