© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 47123
    Prev
    Next
    INDEX
    Explanations

    hyphenated compound words

    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
     nicer
    0.44
     Lest
    0.43
     vouch
    0.42
     beho
    0.42
     जोर
    0.40
    伲
    0.40
     Janice
    0.39
     Jokes
    0.39
     ponies
    0.39
     வரை
    0.38
    POSITIVE LOGITS
    ‐
    0.45
    WebDriver
    0.43
     oltre
    0.43
     অ্যাস
    0.41
    𝗗
    0.41
    avond
    0.40
    理
    0.40
     científicos
    0.39
     Ꭰ
    0.39
    ће
    0.39
    Activations Density 0.005%

    No Known Activations