© 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. 120848
    Prev
    Next
    INDEX
    Explanations

    Highland Park yearbook

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

    phrases followed by specific words

    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
     сер
    0.48
    ிகளைக்
    0.46
     возникает
    0.46
    <unused338>
    0.45
     hört
    0.44
     erhält
    0.43
    监测
    0.43
     রা
    0.43
     си
    0.42
    面积
    0.42
    POSITIVE LOGITS
    pyrazole
    0.44
    滓
    0.41
    товые
    0.40
     Vereinigten
    0.39
    先前
    0.39
    icio
    0.38
    ansir
    0.38
     reopen
    0.37
    omenclature
    0.37
    conventional
    0.37
    Activations Density 0.000%

    No Known Activations