© 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. 31-GEMMASCOPE-2-RES-262K
    7. 41754
    Prev
    Next
    INDEX
    Explanations

    simply, polite, fridge, ventilate, air, bird

    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
    became
    0.47
    *
    0.46
    name
    0.45
    tiny
    0.45
    tsd
    0.45
    ri
    0.45
    are
    0.44
    res
    0.43
     получила
    0.42
    Q
    0.42
    POSITIVE LOGITS
     extravagance
    0.48
     رفت
    0.46
     direcion
    0.45
     mockery
    0.45
     rollback
    0.45
     nonchal
    0.44
     fanatic
    0.43
    𝐞
    0.43
    橇
    0.42
     faça
    0.41
    Activations Density 0.008%

    No Known Activations