© 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. 51550
    Prev
    Next
    INDEX
    Explanations

    challenges and unanswered questions

    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
    ền
    0.47
    ruh
    0.47
    currently
    0.45
    莜
    0.45
     physicality
    0.44
    糇
    0.44
    provides
    0.44
    跗
    0.44
    matter
    0.43
    ۶
    0.43
    POSITIVE LOGITS
     negatives
    0.48
     $
    0.47
     scheda
    0.46
     de
    0.45
     hazards
    0.44
     etc
    0.42
     NOTE
    0.42
     Some
    0.42
     studies
    0.41
     $$
    0.41
    Activations Density 0.006%

    No Known Activations