© 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-16K
    7. 8256
    Prev
    Next
    INDEX
    Explanations

    what's

    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_16k_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
    something
    0.45
    Something
    0.44
     something
    0.41
    thing
    0.40
    Todos
    0.39
    circles
    0.39
    엉
    0.39
    ุย
    0.38
     Ronan
    0.38
     Osh
    0.37
    POSITIVE LOGITS
     happening
    0.55
     произошло
    0.48
     happen
    0.46
     घड
    0.46
     nécessaire
    0.46
     întâm
    0.44
     aconte
    0.43
     féidir
    0.42
     amiss
    0.42
     nécessaires
    0.41
    Activations Density 0.111%

    No Known Activations