© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2095
    Prev
    Next
    INDEX
    Explanations

    No intersection, no solid, no integers

    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_16_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
    j
    1.34
    y
    1.18
     L
    1.16
    w
    1.16
    ă
    1.16
    <0x0D>
    1.14
    g
    1.11
     I
    1.09
     O
    1.09
    um
    1.05
    POSITIVE LOGITS
    ۱
    1.27
    ль
    1.10
    ح
    1.09
    １
    1.09
    ла
    1.06
    तात
    1.05
    기
    1.05
    ले
    1.02
    사
    1.01
    ला
    1.00
    Activations Density 0.670%

    No Known Activations