© 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. 1213
    Prev
    Next
    INDEX
    Explanations

    really unpack your situation / truly listening

    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
    𝐩
    3.22
    𝐧
    3.04
    েই
    3.02
    нци
    2.96
    𝐬
    2.95
    𝐨
    2.88
    𝐜
    2.85
    enfance
    2.84
    𝑛
    2.82
    𝙨
    2.71
    POSITIVE LOGITS
    ignment
    3.59
    로
    3.46
     estate
    3.42
    ところ
    3.08
    politik
    2.97
    ここは
    2.96
    ్
    2.88
     washed
    2.84
    paar
    2.84
    keits
    2.82
    Activations Density 0.717%

    No Known Activations