© 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. 4354
    Prev
    Next
    INDEX
    Explanations

    single letters as labels

    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
     marinated
    0.74
     folklor
    0.74
    คาเด
    0.70
     Nikol
    0.70
    🎇
    0.70
     skept
    0.69
     harmonious
    0.68
     SMP
    0.68
    ამდ
    0.67
    👨
    0.67
    POSITIVE LOGITS
    A
    1.15
     B
    1.10
     A
    1.09
    B
    1.03
    C
    0.96
     C
    0.93
    P
    0.91
    E
    0.90
    Q
    0.90
     D
    0.90
    Activations Density 0.467%

    No Known Activations