© 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. 27313
    Prev
    Next
    INDEX
    Explanations

    tradition was in jeopardy

    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
    сього
    0.41
     Lanes
    0.41
    lanelet
    0.41
    ه
    0.40
    ysta
    0.39
    ini
    0.39
    च्या
    0.39
    achen
    0.38
    綫
    0.38
     Residences
    0.38
    POSITIVE LOGITS
     tableView
    0.49
     suf
    0.43
     ínt
    0.43
     discretized
    0.43
     discret
    0.43
     fic
    0.43
     particolarmente
    0.43
     κο
    0.43
     απο
    0.42
     disables
    0.42
    Activations Density 0.000%

    No Known Activations