© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4046
    Prev
    Next
    INDEX
    Explanations

    LoRA

    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_29_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
     заго
    0.64
    庭
    0.61
     অনুষ্ঠ
    0.60
    ゝ
    0.58
     push
    0.58
     Past
    0.58
     wood
    0.57
     sliding
    0.57
    மையான
    0.56
     Sliding
    0.56
    POSITIVE LOGITS
    Lo
    0.92
     Lo
    0.85
    Rent
    0.85
     lắng
    0.80
    тере
    0.80
    ewe
    0.75
    らの
    0.75
    瑰
    0.75
    హిత
    0.75
    LO
    0.73
    Activations Density 0.047%

    No Known Activations