© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4953
    Prev
    Next
    INDEX
    Explanations

    explaining contrary or exclusive states

    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_16k_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
    ﻜ
    0.52
    )
    0.51
    supplement
    0.44
    宓
    0.44
    ずに
    0.42
     complimented
    0.42
    </i>
    0.42
    Ki
    0.42
    )。
    0.41
    せて
    0.41
    POSITIVE LOGITS
    ☟
    0.52
    ༣
    0.46
     weaning
    0.45
     चक्रवृद्धि
    0.45
     videomuzda
    0.45
     resigning
    0.45
     Embora
    0.45
     ttk
    0.44
     valoración
    0.44
     exhibitors
    0.43
    Activations Density 0.000%

    No Known Activations