© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31725
    Prev
    Next
    INDEX
    Explanations

    direction changes

    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_all/layer_41_width_262k_l0_big
    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
     imbalance
    0.43
    嚣
    0.39
     multiplicative
    0.38
    盗
    0.37
     unbalanced
    0.36
     hypergeometric
    0.35
     Looking
    0.35
     similit
    0.35
     Moved
    0.34
    搬
    0.34
    POSITIVE LOGITS
     direction
    1.07
     reversals
    1.07
     reversing
    1.05
    direction
    1.02
    方向
    1.01
     reverses
    1.01
     направление
    0.99
    Direction
    0.98
     reversal
    0.98
     DIRECTION
    0.93
    Activations Density 0.002%

    No Known Activations