© 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. 13181
    Prev
    Next
    INDEX
    Explanations

    harmful or unethical requests

    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
    0.44
     included
    0.42
     checkbox
    0.42
     {
    0.42
     you
    0.41
     vowel
    0.40
     include
    0.39
     names
    0.39
     Q
    0.39
    默认
    0.39
    POSITIVE LOGITS
    Telefon
    0.47
     profite
    0.47
     rampant
    0.45
     legitim
    0.45
    Produ
    0.44
    Gesellschaft
    0.44
    戕
    0.43
     extraordin
    0.42
    社會
    0.42
     სახელმწიფ
    0.41
    Activations Density 0.334%

    No Known Activations