© 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. 42516
    Prev
    Next
    INDEX
    Explanations

    em, embrace, embitter, embody

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

    Embrace

    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
    amas
    0.60
    n
    0.60
    '
    0.60
    inen
    0.59
    p
    0.58
    डी
    0.55
    е
    0.55
    ि
    0.55
    ivasena
    0.54
    of
    0.53
    POSITIVE LOGITS
     EMB
    1.05
     EMP
    0.84
    Em
    0.79
     em
    0.74
     emb
    0.74
     Em
    0.73
     Emb
    0.72
     Embr
    0.70
     emp
    0.67
     Embar
    0.67
    Activations Density 0.051%

    No Known Activations