© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12591
    Prev
    Next
    INDEX
    Explanations

    sometimes or cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CELL
    0.46
    鿆
    0.46
    믄
    0.46
    reve
    0.44
     putra
    0.44
    Reve
    0.43
    ுகிறது
    0.43
    セル
    0.42
    אי
    0.42
    尟
    0.42
    POSITIVE LOGITS
     pd
    0.43
     पर्यवे
    0.41
     habrá
    0.41
     tř
    0.41
     benötigt
    0.40
     PDGF
    0.40
     merits
    0.39
     χρει
    0.39
     δ
    0.38
     múltiples
    0.38
    Activations Density 0.001%

    No Known Activations