© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 70969
    Prev
    Next
    INDEX
    Explanations

    enhanced abilities

    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
     Duty
    0.48
     Contents
    0.47
    '
    0.47
     Object
    0.42
    Contents
    0.42
     Instruction
    0.41
     Management
    0.40
     duty
    0.40
    説
    0.40
     That
    0.40
    POSITIVE LOGITS
     phosphory
    0.55
     अलं
    0.51
    FAPI
    0.50
     અનુ
    0.50
    ırm
    0.49
    োগ্রাফ
    0.49
    രുവന
    0.48
     gimnas
    0.47
    getSaveLocation
    0.47
    mobilpay
    0.47
    Activations Density 0.000%

    No Known Activations