© 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. 149167
    Prev
    Next
    INDEX
    Explanations

    outdated electronics or trash

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

    therapists can choose

    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
    屆
    0.48
    حدة
    0.47
     potrà
    0.45
    小的
    0.43
    第一題
    0.43
    nicu
    0.41
    騰
    0.41
    flat
    0.40
     gerar
    0.40
    KX
    0.39
    POSITIVE LOGITS
     ო
    0.48
     deri
    0.48
     emf
    0.46
     כן
    0.46
     elementi
    0.46
     LCCN
    0.45
    akot
    0.45
     electroneg
    0.45
    𝓭
    0.44
     ओ
    0.44
    Activations Density 0.000%

    No Known Activations