© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-16K
    4. 325
    Prev
    Next
    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     করিনি
    0.68
     করেনি
    0.65
    บัติ
    0.63
     FIXME
    0.63
    륭
    0.62
    添加到
    0.59
    랗
    0.59
     தரும்
    0.55
    ன்மைய
    0.55
     Перейти
    0.55
    POSITIVE LOGITS
    ’
    1.63
     are
    1.60
    '
    1.51
     is
    1.30
     ARE
    1.12
     were
    1.02
     Are
    1.00
     estão
    0.97
     هستند
    0.95
     lies
    0.94
    Activations Density 0.419%

    No Known Activations