© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2750
    Prev
    Next
    INDEX
    Explanations

    respected experts and groups

    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_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
    Projeto
    0.89
     künstler
    0.84
    ⩾
    0.81
    Proyecto
    0.79
     художе
    0.77
     Projeto
    0.73
    Glor
    0.72
    𝒮
    0.71
     αγ
    0.71
    proyecto
    0.70
    POSITIVE LOGITS
     thought
    1.58
     Thought
    1.51
    Thought
    1.43
    thought
    1.37
     industry
    1.27
     Industry
    1.19
    Industry
    1.14
    industry
    1.12
     LinkedIn
    1.08
     CIO
    1.07
    Activations Density 0.481%

    No Known Activations