© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10490
    Prev
    Next
    INDEX
    Explanations

    your brand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    𒅜
    1.61
    ꗚ
    1.60
    opencamer
    1.60
    AutoStabilise
    1.60
    𒑜
    1.59
    𒍭
    1.59
    FBSDKBridgeAPI
    1.59
    courseSurvey
    1.59
     Polynucleaires
    1.58
    )$\--
    1.58
    POSITIVE LOGITS
    0.90
     O
    0.90
    【
    0.79
    真
    0.78
     P
    0.77
     G
    0.76
    ↵
    0.75
     L
    0.74
    明
    0.73
    ళ్ళు
    0.73
    Activations Density 0.007%

    No Known Activations