© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117435
    Prev
    Next
    INDEX
    Explanations

    proceed ahead, for sale

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

    contrasting concepts

    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
     $\
    0.50
    \
    0.48
    agi
    0.47
    antz
    0.44
    atu
    0.43
    }=\
    0.43
    ReadOnly
    0.43
    man
    0.42
     i
    0.42
    <
    0.42
    POSITIVE LOGITS
    叁章
    0.51
     เนาะ
    0.50
     그런데
    0.49
     supérieurs
    0.49
     მაგრამ
    0.49
    ຜະລ
    0.49
    殮
    0.47
    薁
    0.46
     balconies
    0.46
    㑹
    0.46
    Activations Density 0.001%

    No Known Activations