© 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. 27361
    Prev
    Next
    INDEX
    Explanations

    comparative phrases using than

    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
     клиентов
    0.39
    /
    0.39
     العديد
    0.36
    due
    0.36
    🥞
    0.36
     propietarios
    0.35
    United
    0.35
    -
    0.35
    ഡ്
    0.35
    ボー
    0.35
    POSITIVE LOGITS
     constru
    0.47
     explic
    0.45
    gramModel
    0.43
     ersten
    0.42
     absur
    0.41
     utterance
    0.40
     nicht
    0.39
     negation
    0.39
     ontological
    0.39
     annak
    0.39
    Activations Density 0.002%

    No Known Activations