© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167502
    Prev
    Next
    INDEX
    Explanations

    adjusted values

    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_262k_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
    行
    0.37
     showers
    0.37
    umers
    0.37
    ربع
    0.37
    shower
    0.37
    driver
    0.36
     taf
    0.36
    டையே
    0.36
     furnaces
    0.36
    偈
    0.35
    POSITIVE LOGITS
     adjusted
    1.59
    adjusted
    1.41
     Adjusted
    1.35
    Adjust
    1.31
     adjusting
    1.28
     adjusts
    1.27
     adjust
    1.26
     Adjust
    1.22
     ajust
    1.16
     ADJUST
    1.16
    Activations Density 0.039%

    No Known Activations