© 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. 71836
    Prev
    Next
    INDEX
    Explanations

    evaluating qualities other than character

    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
    Dream
    0.57
     Dream
    0.53
     Symmetric
    0.52
     साझे
    0.49
    jším
    0.48
    㥳
    0.47
     इन्
    0.47
    䫒
    0.47
     فتح
    0.46
    zano
    0.46
    POSITIVE LOGITS
     butts
    0.49
     oppressive
    0.47
     pierde
    0.46
     encouraging
    0.44
     oriented
    0.43
     unpleasant
    0.43
     abusive
    0.43
     lose
    0.43
     unm
    0.42
     unfit
    0.42
    Activations Density 0.001%

    No Known Activations