© 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. 44908
    Prev
    Next
    INDEX
    Explanations

    text formatting and structure

    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
    lessness
    0.58
    hashtag
    0.55
     haught
    0.53
    ism
    0.50
    longitude
    0.49
    rie
    0.49
    𝔪
    0.48
    𝗱
    0.47
    continu
    0.46
    𝘔
    0.46
    POSITIVE LOGITS
     Fibre
    0.48
     Prostate
    0.47
     Hydro
    0.46
     Ebay
    0.45
     rendimiento
    0.44
     effettuare
    0.44
     Dental
    0.43
     thậm
    0.43
     Ultra
    0.43
     Auto
    0.42
    Activations Density 0.006%

    No Known Activations