© 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-16K
    7. 10379
    Prev
    Next
    INDEX
    Explanations

    long-term and permanent

    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_16k_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
    beest
    0.46
    áže
    0.44
    -"+
    0.44
     مباشرة
    0.44
    -
    0.44
     Тере
    0.43
     directement
    0.43
     سريع
    0.42
    %");
    0.41
     directe
    0.41
    POSITIVE LOGITS
     Permanent
    1.06
     permanent
    1.05
    Permanent
    1.02
    permanent
    1.01
     longterm
    0.99
     Perman
    0.91
     permanently
    0.88
    Perman
    0.88
     स्थायी
    0.87
     perman
    0.86
    Activations Density 0.149%

    No Known Activations