© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11601
    Prev
    Next
    INDEX
    Explanations

    structured lists with separators

    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
    sko
    1.41
    (-\
    1.39
     prueba
    1.39
    ाई
    1.32
    (.
    1.25
     ong
    1.24
    ことができる
    1.24
    ことがある
    1.23
    咪
    1.22
    tt
    1.22
    POSITIVE LOGITS
    ALITY
    1.51
     getContentPane
    1.49
     taxonomy
    1.48
    enhancing
    1.46
     longitude
    1.44
    asat
    1.42
    न
    1.42
     ইন্দিরা
    1.41
    на
    1.35
    effectiveness
    1.35
    Activations Density 0.000%

    No Known Activations