© 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-65K
    7. 47896
    Prev
    Next
    INDEX
    Explanations

    counting numbers

    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_65k_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
    enang
    0.43
    पाल
    0.37
    textsc
    0.37
    <unused470>
    0.37
    OO
    0.36
     nii
    0.36
     sejumlah
    0.35
    𝗟
    0.35
    ་་
    0.35
    㵴
    0.35
    POSITIVE LOGITS
     bucks
    0.43
     nine
    0.38
    nine
    0.38
    moved
    0.38
     planned
    0.37
    協力
    0.37
     momentum
    0.36
     neun
    0.35
    radiated
    0.35
    adora
    0.35
    Activations Density 0.003%

    No Known Activations