© 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. 27272
    Prev
    Next
    INDEX
    Explanations

    80/20 rule percentages

    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
    𝒐
    0.45
    јединачна
    0.45
     визна
    0.44
     flipped
    0.42
     reaffirmed
    0.42
    𝑮
    0.41
     quantified
    0.41
    🎑
    0.41
    🕤
    0.40
     mitigating
    0.40
    POSITIVE LOGITS
     cinder
    0.46
     Scrolls
    0.46
    sponsor
    0.46
    La
    0.44
     자신의
    0.43
    มา
    0.43
    t
    0.42
     castillo
    0.42
    lla
    0.42
     Cach
    0.42
    Activations Density 0.011%

    No Known Activations