© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20391
    Prev
    Next
    INDEX
    Explanations

    expected use or grades

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

    Absurdism, existentialism, authenticity

    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
    «,
    0.50
     bellissimo
    0.48
    <0xEA>
    0.48
    §
    0.47
    wa
    0.47
    ÊN
    0.47
    emb
    0.46
    ellen
    0.45
    ġ
    0.45
    غي
    0.45
    POSITIVE LOGITS
     일을
    0.53
     शरण
    0.50
     cli
    0.46
    withId
    0.46
     일이
    0.44
     खिल
    0.43
    ্ষিক
    0.42
     유사
    0.42
     얼
    0.42
     colorless
    0.42
    Activations Density 0.000%

    No Known Activations