© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135884
    Prev
    Next
    INDEX
    Explanations

    Age, what, them

    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
     dino
    0.44
    轱
    0.44
     Galbraith
    0.43
     Hind
    0.40
     ঈ
    0.40
     assemblage
    0.38
     vases
    0.38
     ayahuasca
    0.38
     топлива
    0.38
    from
    0.38
    POSITIVE LOGITS
     permit
    0.40
    を進
    0.38
     Accordingly
    0.38
    REC
    0.37
    >-</
    0.37
    пора
    0.37
             
    0.36
     Constitution
    0.36
    ﻬ
    0.35
     der
    0.35
    Activations Density 0.000%

    No Known Activations