© 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-16K
    7. 2240
    Prev
    Next
    INDEX
    Explanations

    C/C++ code snippets

    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_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
     crushed
    0.82
     delighted
    0.76
     Brain
    0.75
     E
    0.74
     disqualified
    0.74
     Presented
    0.73
     renamed
    0.72
     CS
    0.72
     ஹை
    0.70
    <unused1772>
    0.70
    POSITIVE LOGITS
    -
    0.94
    MEs
    0.90
    ICs
    0.87
    Ps
    0.85
    형
    0.81
    UID
    0.81
    Ž
    0.81
    檚
    0.80
    Ç
    0.79
    Vs
    0.78
    Activations Density 0.210%

    No Known Activations