© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62268
    Prev
    Next
    INDEX
    Explanations

    predicting next word or token

    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_65k_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
    A
    0.42
    ayanti
    0.42
    更好的
    0.41
    િ
    0.41
    后
    0.41
    米
    0.41
     diketahui
    0.40
     lebih
    0.39
     لديك
    0.39
    ','
    0.39
    POSITIVE LOGITS
     తమిళ
    0.46
    binoculars
    0.45
    ვის
    0.43
     méd
    0.42
    نىڭ
    0.42
     AUGUST
    0.42
     objecting
    0.42
    誐
    0.41
     mécanisme
    0.41
    тың
    0.41
    Activations Density 0.001%

    No Known Activations