© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 62517
    Prev
    Next
    INDEX
    Explanations

    Doing a

    np_acts-logits-general · gemini-2.5-flash-lite

    events after upgrades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Editable
    0.49
     চলতি
    0.49
    
    0.49
    Countdown
    0.48
    我們先
    0.48
    מ
    0.45
    বা
    0.45
    ových
    0.45
     احنا
    0.44
    احنا
    0.44
    POSITIVE LOGITS
    c
    0.51
    xz
    0.44
     Strept
    0.43
     SIINFEKL
    0.42
     zakresie
    0.41
     nephew
    0.41
     newfound
    0.41
    iella
    0.41
     landed
    0.41
     markedly
    0.40
    Activations Density 0.000%

    No Known Activations