© 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. 222184
    Prev
    Next
    INDEX
    Explanations

    property, legal, financial

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

    calculating, finding, elected, teeth

    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
    IC
    0.51
     Gertrude
    0.50
    ຜະລິດຕະພັນ
    0.50
     organismo
    0.49
    𝐂
    0.47
    Tit
    0.47
    ICK
    0.46
    幼
    0.46
    7
    0.46
    Ｑ
    0.45
    POSITIVE LOGITS
     justifyContent
    0.46
     LOCCTR
    0.45
    氇
    0.44
     је
    0.43
     proxy
    0.43
    razione
    0.42
     നമു
    0.42
     отношение
    0.42
     কামান
    0.42
     упра
    0.41
    Activations Density 0.000%

    No Known Activations