© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9668
    Prev
    Next
    INDEX
    Explanations

    parameters for algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
    Д
    3.61
    м
    3.18
    
    2.76
     meninas
    2.71
    ্বল
    2.70
    त
    2.66
    👏👏
    2.65
     quede
    2.63
     affrontare
    2.59
    జేపీ
    2.58
    POSITIVE LOGITS
    ••••
    4.22
    .•
    4.20
    ••
    4.11
    𝚗
    3.65
    𝚛
    3.42
    𝚕
    3.17
    𝚖
    3.02
    𝚝
    2.92
    𝚍
    2.89
    𝚜
    2.76
    Activations Density 0.020%

    No Known Activations