© 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-65K
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    different, specific, harmful, same characterization

    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_65k_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
    Che
    0.35
     ajoute
    0.35
    ìn
    0.34
    re
    0.33
    ajouter
    0.33
     össze
    0.33
     inconvén
    0.32
    讽
    0.32
    Good
    0.32
     devolución
    0.32
    POSITIVE LOGITS
     timescales
    0.43
     timescale
    0.43
     topologies
    0.42
     nature
    0.41
     timeframe
    0.40
     communication
    0.40
     architectures
    0.40
     behaviour
    0.40
     conceptions
    0.40
     deploying
    0.39
    Activations Density 0.171%

    No Known Activations