© 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. 17750
    Prev
    Next
    INDEX
    Explanations

    specific terms followed by descriptors

    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
    …’
    0.47
     풍
    0.46
     Kết
    0.46
    (
    0.44
    风
    0.43
    penas
    0.43
     τὸ
    0.42
     삭제
    0.42
    !<
    0.41
    )<
    0.41
    POSITIVE LOGITS
    Wave
    0.44
    Payments
    0.44
    GAM
    0.44
     waveform
    0.43
    k
    0.43
    Signed
    0.42
    MessageNow
    0.42
    PA
    0.41
    ünftig
    0.41
     payments
    0.41
    Activations Density 0.002%

    No Known Activations