© 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. 31767
    Prev
    Next
    INDEX
    Explanations

    pathname and home directory references

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

    file path existence checks

    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
     Saves
    0.42
     Motivational
    0.42
     Libya
    0.41
    ronaut
    0.41
    ``
    0.40
     recogida
    0.39
    currentIndex
    0.38
    jgl
    0.38
     necesitar
    0.38
     colspan
    0.37
    POSITIVE LOGITS
     проду
    0.44
    🏟
    0.44
     Dois
    0.42
    店頭
    0.42
    ยิน
    0.42
    Kre
    0.42
    ofile
    0.41
    🏗
    0.41
    ⚒
    0.41
    氳
    0.40
    Activations Density 0.001%

    No Known Activations