© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    more concise detailed

    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
     важней
    0.51
     миро
    0.43
     milhares
    0.42
     countless
    0.41
     milliers
    0.40
    󰡔
    0.40
     İşte
    0.40
     thousands
    0.39
    née
    0.39
     _______
    0.39
    POSITIVE LOGITS
     more
    0.69
     более
    0.65
     slightly
    0.60
     थोड़ा
    0.60
     більш
    0.58
     another
    0.57
     bardziej
    0.57
     lebih
    0.57
     વધુ
    0.57
     మరింత
    0.57
    Activations Density 0.712%

    No Known Activations