© 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. 21094
    Prev
    Next
    INDEX
    Explanations

    installing, center of, providing product, rock chip

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

    initiating and

    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
     (`
    0.44
     expedite
    0.43
     Remarkably
    0.42
     debacle
    0.41
     minuscule
    0.41
     redux
    0.41
     silam
    0.40
     okam
    0.40
     ```
    0.40
     eighth
    0.40
    POSITIVE LOGITS
    差别
    0.55
    我们需要
    0.53
     большинство
    0.52
    例えば
    0.51
     birçok
    0.51
     многи
    0.50
     অনেকে
    0.50
    大多数
    0.50
    যেমন
    0.49
     meeste
    0.48
    Activations Density 0.000%

    No Known Activations