© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52377
    Prev
    Next
    INDEX
    Explanations

    dumpster related words

    np_acts-logits-general · gemini-2.5-flash-lite

    align math equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    0.41
    ثير
    0.39
    dh
    0.39
    하시
    0.39
    쌓
    0.38
    e
    0.38
    </h3>
    0.38
    جاد
    0.37
     bhe
    0.37
    q
    0.37
    POSITIVE LOGITS
     পরিষদের
    0.51
    ানা
    0.48
    刓
    0.45
    Sqrt
    0.43
    Mul
    0.40
    Lanc
    0.39
    㓦
    0.39
    KeyboardMarkup
    0.39
     作詞
    0.39
    LDL
    0.39
    Activations Density 0.000%

    No Known Activations