© 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. 172671
    Prev
    Next
    INDEX
    Explanations

    long term complications, student loan, hearing loss, latest setback

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

    technical instructions like `filetype:` or `pdf`

    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
     précieux
    0.51
     propietarios
    0.50
    たち
    0.49
    <tr>
    0.48
     cohé
    0.46
    exclusions
    0.46
     みたい
    0.46
    éric
    0.45
    சொ
    0.45
    اهای
    0.45
    POSITIVE LOGITS
    Hour
    0.46
    Nicholas
    0.43
    VILLE
    0.42
    }}$$
    0.42
     قناه
    0.41
     HOURS
    0.41
     hour
    0.41
     Hours
    0.41
    ั่วโมง
    0.41
    Quem
    0.40
    Activations Density 0.000%

    No Known Activations