© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53500
    Prev
    Next
    INDEX
    Explanations

    contrast and commonality

    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
    ر
    0.42
     receiving
    0.38
    0.38
     parchment
    0.38
    لمانيا
    0.37
     wherever
    0.37
     mixture
    0.37
     teaching
    0.36
     Align
    0.36
     streams
    0.36
    POSITIVE LOGITS
    נ
    0.51
    可谓
    0.51
     repre
    0.50
     honti
    0.50
    Salir
    0.50
    Heart
    0.49
    Quel
    0.49
    Glor
    0.49
    ăpadă
    0.49
    É
    0.49
    Activations Density 0.005%

    No Known Activations