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

    Neuronpedia

    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. 53700
    Prev
    Next
    INDEX
    Explanations

    enjoying, thriving, easing

    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
    0.51
    气体
    0.50
     kandid
    0.49
    siswa
    0.48
    龅
    0.48
     프로그램을
    0.47
    ᴏ
    0.47
     परीक्ष
    0.46
     muszą
    0.46
    ORS
    0.46
    POSITIVE LOGITS
     dissociated
    0.46
     indist
    0.45
     comparable
    0.44
     similar
    0.42
    0.42
     مرتبط
    0.41
     Similar
    0.41
     role
    0.41
     counterpart
    0.40
     Finances
    0.40
    Activations Density 0.005%

    No Known Activations