© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10194
    Prev
    Next
    INDEX
    Explanations

    revivatone

    np_acts-logits-general · gemini-2.5-flash-lite

    offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ිත
    0.46
    ارج
    0.44
    पीरियंस
    0.43
    摈
    0.42
     সম্মিল
    0.41
    绎
    0.41
    戽
    0.40
     দুর্নীতি
    0.40
     مالک
    0.39
     бібліоте
    0.39
    POSITIVE LOGITS
     Tats
    0.43
    <strong>
    0.42
     Umm
    0.41
     hims
    0.41
     control
    0.40
    cov
    0.40
    current
    0.40
     appreciation
    0.39
     rushing
    0.39
    kid
    0.39
    Activations Density 0.003%

    No Known Activations