© 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. 199578
    Prev
    Next
    INDEX
    Explanations

    online presence and services

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

    feeling uneasy or overwhelmed

    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
    DbType
    0.44
    tDBOutput
    0.42
    }`));
    0.41
    னின்
    0.41
     لمن
    0.41
     القرآن
    0.41
     acquires
    0.39
     Existing
    0.39
    <0x04>
    0.39
    }}}=
    0.39
    POSITIVE LOGITS
    op
    0.51
     unwell
    0.50
    analy
    0.48
    mo
    0.47
     incont
    0.47
     Boucher
    0.46
     Fukuoka
    0.45
     Fare
    0.45
    ма
    0.45
     Bale
    0.45
    Activations Density 0.001%

    No Known Activations