© 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. 11048
    Prev
    Next
    INDEX
    Explanations

    detects negation

    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
     trusts
    0.30
     Gets
    0.30
    /
    0.28
    Au
    0.26
     knows
    0.25
     cares
    0.25
    รู้
    0.25
    ittest
    0.25
     Pays
    0.24
    ails
    0.24
    POSITIVE LOGITS
     hề
    0.38
    withstanding
    0.36
     unduly
    0.35
     disdain
    0.34
     superfluous
    0.31
    preliquidacion
    0.30
    髖
    0.29
     புதிய
    0.29
    含ま
    0.29
     adversely
    0.28
    Activations Density 0.046%

    No Known Activations