© 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. 2228
    Prev
    Next
    INDEX
    Explanations

    feature comparison and distinction

    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
    藿
    0.37
    borist
    0.34
    шов
    0.34
     taker
    0.33
     Nor
    0.33
     saison
    0.33
     Bhagavato
    0.32
    ையோ
    0.32
     psychologist
    0.32
     coroner
    0.31
    POSITIVE LOGITS
    }%
    0.31
    jsx
    0.30
    cores
    0.29
    {}
    0.29
    ({})
    0.29
    ناك
    0.28
     [])
    0.28
    )</
    0.28
    mf
    0.28
    illac
    0.27
    Activations Density 0.006%

    No Known Activations