© 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. 11851
    Prev
    Next
    INDEX
    Explanations

    Dear followed by names/titles

    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
    k
    3.46
    अ
    3.34
    ยัง
    2.94
    म
    2.92
     áll
    2.72
     ă
    2.69
    চ
    2.63
    ସ
    2.58
    𝚍
    2.56
    𝟎
    2.53
    POSITIVE LOGITS
    an
    3.08
     emeritus
    2.90
    uhi
    2.76
     mistaken
    2.76
    NSLog
    2.73
    ंबर्स
    2.71
    formatics
    2.71
    gam
    2.68
    ודי
    2.62
    quakes
    2.62
    Activations Density 0.018%

    No Known Activations