© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198021
    Prev
    Next
    INDEX
    Explanations

    company status

    np_acts-logits-general · gemini-2.5-flash-lite

    sequences, counts, lengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.48
    赏
    0.47
    Win
    0.46
    ιών
    0.46
    ဖြ
    0.44
    Especific
    0.43
    Red
    0.42
    ради
    0.42
    ۲
    0.42
    Anthrop
    0.41
    POSITIVE LOGITS
     gacche
    0.54
     bagged
    0.52
    ዎት
    0.52
     మద్య
    0.51
     سي
    0.51
    餑
    0.50
     ಒಬ್ಬ
    0.50
     রিলি
    0.49
     prestación
    0.49
     ક્
    0.48
    Activations Density 0.000%

    No Known Activations