© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50459
    Prev
    Next
    INDEX
    Explanations

    time and conditions

    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
     Competitive
    0.47
     CIRC
    0.45
    内存
    0.42
     Contracts
    0.42
    𝘵
    0.41
    MRC
    0.41
     Shed
    0.41
    应
    0.40
    quality
    0.40
    WAR
    0.39
    POSITIVE LOGITS
     panahon
    0.46
    ahmatullahi
    0.46
     teléfonos
    0.45
     priceless
    0.43
     cellphone
    0.43
    forgettable
    0.43
     invariable
    0.42
     telefone
    0.42
     smartphone
    0.42
    artet
    0.42
    Activations Density 0.007%

    No Known Activations