© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9169
    Prev
    Next
    INDEX
    Explanations

    steps and intervals

    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_40_width_16k_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
    ंव
    0.38
    ллина
    0.38
     infix
    0.38
     በላይ
    0.37
     عشق
    0.36
    荽
    0.36
    过去
    0.35
    әй
    0.35
    ሪ
    0.35
     Josie
    0.35
    POSITIVE LOGITS
     intervals
    1.20
     Intervals
    1.11
     interval
    1.09
    间隔
    1.09
     increments
    1.08
    interval
    1.06
    intervals
    1.06
     intervalos
    1.04
     spacing
    1.03
     increment
    1.02
    Activations Density 0.281%

    No Known Activations