© 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. 25649
    Prev
    Next
    INDEX
    Explanations

    topics or entities followed by context

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

    technical topics and 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
     nhưng
    0.38
     लेकिन
    0.36
     крайне
    0.36
     ซึ่ง
    0.35
    arakat
    0.35
    jours
    0.35
    ガ
    0.35
    の方が
    0.34
    °,
    0.33
    வதற்காக
    0.33
    POSITIVE LOGITS
    </h2>
    0.57
    </h1>
    0.45
    ؟
    0.45
    ๎
    0.39
    </h3>
    0.38
     ધ્યા
    0.38
    釟
    0.38
    Permalink
    0.38
    
    0.38
    ⤒
    0.38
    Activations Density 0.030%

    No Known Activations