© 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. 99163
    Prev
    Next
    INDEX
    Explanations

    daily active

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

    gas fees

    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
     futuras
    0.55
     nuestro
    0.50
     regres
    0.47
     comorbidities
    0.46
     ⋮
    0.46
     genomic
    0.46
     scenarios
    0.45
     burials
    0.45
     gên
    0.45
     future
    0.45
    POSITIVE LOGITS
     መጠን
    0.46
    ਔ
    0.45
    影响
    0.43
     Dating
    0.42
    布置
    0.42
    ку
    0.41
     मकान
    0.41
    טה
    0.40
    笼
    0.40
    影响力
    0.40
    Activations Density 0.003%

    No Known Activations