© 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. 60814
    Prev
    Next
    INDEX
    Explanations

    memorable, unforgettable, lingers, stuck

    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
    엎
    0.42
    尣
    0.39
    Rosen
    0.39
    angleOf
    0.37
    сим
    0.37
    ”)
    0.37
     lienzo
    0.37
    衍生
    0.37
    岑
    0.37
     ज्ये
    0.37
    POSITIVE LOGITS
     memorable
    1.48
     unforgettable
    1.28
     lingers
    1.20
     lingered
    1.17
     stuck
    1.15
     sticking
    1.06
     lingering
    1.06
     stick
    1.05
     stayed
    1.05
     linger
    1.05
    Activations Density 0.001%

    No Known Activations