© 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. 22-GEMMASCOPE-2-RES-262K
    7. 4621
    Prev
    Next
    INDEX
    Explanations

    translation and discussion

    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_22_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
    మవు
    0.59
    及其
    0.59
    力和
    0.56
     maupun
    0.56
     avete
    0.55
    皇
    0.55
    ági
    0.55
     अपन
    0.53
    하신
    0.52
     адам
    0.52
    POSITIVE LOGITS
     it
    1.40
     them
    1.07
     things
    0.94
    它
    0.92
    มัน
    0.91
     इसे
    0.89
     এটিকে
    0.83
    It
    0.83
     It
    0.82
     Things
    0.81
    Activations Density 0.000%

    No Known Activations