© 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. 31-GEMMASCOPE-2-RES-65K
    7. 50917
    Prev
    Next
    INDEX
    Explanations

    solving equations step-by-step

    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
     succumbed
    0.48
     succumb
    0.48
     disillusioned
    0.44
     mainstream
    0.43
     ushered
    0.42
     fraught
    0.41
    ‿
    0.41
     cherished
    0.40
     stemming
    0.40
     embroiled
    0.40
    POSITIVE LOGITS
     anionic
    0.49
     قبل
    0.48
    From
    0.47
    Proper
    0.47
     किंवा
    0.46
    When
    0.46
     During
    0.46
    Before
    0.45
    邡
    0.45
    BEFORE
    0.44
    Activations Density 0.007%

    No Known Activations