© 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. 118820
    Prev
    Next
    INDEX
    Explanations

    corruption, cultivar, estimate

    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
     Parliament
    0.41
    𝗡
    0.40
    available
    0.38
     已
    0.38
     wordArray
    0.38
     }{}_{\
    0.38
     }^{*}$
    0.38
    
    0.38
     Sudah
    0.38
     ထ
    0.38
    POSITIVE LOGITS
     inwoners
    0.39
     husbandry
    0.37
    cieron
    0.36
     shovel
    0.36
    ινων
    0.36
     inhabitants
    0.36
     slippery
    0.36
    渡し
    0.36
     possess
    0.35
     frères
    0.35
    Activations Density 0.000%

    No Known Activations