© 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. 50040
    Prev
    Next
    INDEX
    Explanations

    guided by negative outcomes

    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
    shaders
    0.46
    assertion
    0.44
    PWD
    0.43
    ie
    0.43
    濬
    0.42
     Chemistry
    0.42
    ABCD
    0.42
    溟
    0.41
    chemistry
    0.41
    对外
    0.41
    POSITIVE LOGITS
     admire
    0.46
     reminis
    0.45
     averse
    0.43
     malheureusement
    0.42
     unfortunately
    0.42
     expire
    0.42
     sadly
    0.42
    เสียหาย
    0.42
     republished
    0.42
     historiques
    0.41
    Activations Density 0.002%

    No Known Activations