© 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-16K
    7. 2341
    Prev
    Next
    INDEX
    Explanations

    want to investigate

    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_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
    7
    1.66
     relentless
    1.65
    5
    1.54
    8
    1.51
    6
    1.49
     profound
    1.44
    9
    1.44
    0
    1.44
     crescita
    1.42
     colossal
    1.42
    POSITIVE LOGITS
    ทั่วไป
    1.43
    名称
    1.42
    TGFuZ
    1.38
    を使用
    1.26
    を使用して
    1.25
    ដែល
    1.20
    Information
    1.18
    名稱
    1.18
     verwenden
    1.17
    넣
    1.16
    Activations Density 4.188%

    No Known Activations