© 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. 71622
    Prev
    Next
    INDEX
    Explanations

    handling safe area

    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
    ,
    0.46
     everything
    0.45
    itious
    0.43
    igent
    0.42
    maketitle
    0.41
    igraph
    0.40
    equiv
    0.40
     spelled
    0.39
    it
    0.38
     正
    0.38
    POSITIVE LOGITS
     कैलो
    0.54
    Chlor
    0.46
    군
    0.45
    皞
    0.45
    Cooldown
    0.44
    वायरमेंट
    0.44
    ས
    0.43
    DAT
    0.43
    TEMPERATURE
    0.43
    Ö
    0.42
    Activations Density 0.000%

    No Known Activations