© 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. 51805
    Prev
    Next
    INDEX
    Explanations

    end of sentence or code

    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
    ロマ
    0.48
    ъ
    0.42
    పో
    0.42
    リエ
    0.42
    ドア
    0.41
     ド
    0.40
     ದೇಹ
    0.40
    opath
    0.39
    メモ
    0.39
    ্যাস
    0.39
    POSITIVE LOGITS
    的
    0.51
    sourceEncoding
    0.51
     efter
    0.50
    後的
    0.46
     suppl
    0.46
    และ
    0.46
    子的
    0.46
    i
    0.46
     och
    0.45
    建筑物
    0.45
    Activations Density 0.002%

    No Known Activations