© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84995
    Prev
    Next
    INDEX
    Explanations

    longest substring or subsequence

    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_40_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
    त्रेयी
    0.48
    רץ
    0.41
    avers
    0.40
     அமைச்சர்
    0.40
    𒁳
    0.40
     longo
    0.39
    номи
    0.39
    婜
    0.39
    stylesheet
    0.38
     (|
    0.38
    POSITIVE LOGITS
     True
    0.46
     foreign
    0.41
     diversity
    0.41
     Prohibition
    0.40
     part
    0.40
     space
    0.39
     line
    0.39
    True
    0.39
     prohibition
    0.39
     DEI
    0.38
    Activations Density 0.002%

    No Known Activations