© 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. 47147
    Prev
    Next
    INDEX
    Explanations

    looking for a community match

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

    important consideration, excellent candidates

    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
     által
    0.45
    द्भ
    0.45
     сад
    0.45
    是一家
    0.43
     माली
    0.43
    鹘
    0.43
     руку
    0.41
     криптовалю
    0.41
    绡
    0.41
    瞽
    0.41
    POSITIVE LOGITS
    lbl
    0.55
     welches
    0.48
    ):
    0.46
     reject
    0.46
     exceeds
    0.46
    )
    0.46
            
    0.46
    deleted
    0.46
     lbl
    0.45
    arg
    0.45
    Activations Density 0.000%

    No Known Activations