© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 52506
    Prev
    Next
    INDEX
    Explanations

    best practices or right way

    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
    s
    0.52
    V
    0.49
     I
    0.49
     M
    0.48
    B
    0.45
    I
    0.42
    II
    0.41
                                  
    0.41
    is
    0.41
    ints
    0.41
    POSITIVE LOGITS
     adoration
    0.53
     muzy
    0.52
    łącznie
    0.52
    świę
    0.51
     repulsion
    0.50
     fiabilité
    0.49
     admiration
    0.49
    仿佛
    0.48
     poważ
    0.48
     którym
    0.47
    Activations Density 0.011%

    No Known Activations