© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 37634
    Prev
    Next
    INDEX
    Explanations

    into one / hitting smaller / by perceptual

    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
     merciless
    0.50
    aparikkh
    0.49
     да
    0.47
     disguise
    0.47
     lähe
    0.46
    ğimiz
    0.45
    遐
    0.45
     разнови
    0.45
     scarcely
    0.44
    inairement
    0.44
    POSITIVE LOGITS
    repeat
    0.50
    act
    0.47
    can
    0.47
    第
    0.45
     voldoende
    0.45
    2
    0.45
    1
    0.44
    form
    0.44
    response
    0.44
    display
    0.44
    Activations Density 0.007%

    No Known Activations