© 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. 15045
    Prev
    Next
    INDEX
    Explanations

    mathematical notation ($1, (f, `text`)

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

    mathematical expressions with variables

    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
    ène
    0.57
     avril
    0.56
    ry
    0.54
    ages
    0.54
    </td>
    0.53
     and
    0.53
     alleles
    0.52
    ties
    0.52
     ovary
    0.52
     inconn
    0.50
    POSITIVE LOGITS
    ൈ
    0.65
     中
    0.61
    леку
    0.60
    هي
    0.58
    니다
    0.57
     מת
    0.56
    儁
    0.56
    LiveData
    0.55
     يك
    0.55
     Хер
    0.55
    Activations Density 0.000%

    No Known Activations