© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13263
    Prev
    Next
    INDEX
    Explanations

    expressing a need or request

    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_31_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
     confidentialité
    0.39
     społ
    0.37
    !=
    0.36
     examining
    0.36
    िति
    0.36
     dissent
    0.36
     dissociation
    0.35
     Targeting
    0.35
    albeit
    0.34
     falsch
    0.34
    POSITIVE LOGITS
    韵
    0.40
    伒
    0.39
     Beziehung
    0.37
    ză
    0.37
    镜头
    0.37
     নামাজের
    0.37
    んですが
    0.36
     చక్క
    0.36
     பார்வை
    0.36
    ペイ
    0.35
    Activations Density 0.001%

    No Known Activations