© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6098
    Prev
    Next
    INDEX
    Explanations

    **2. X:**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     up
    0.71
    Up
    0.68
    ochial
    0.66
    ]++;
    0.65
     krypt
    0.64
    눕
    0.64
     prayers
    0.64
    fragen
    0.64
    mach
    0.63
    łej
    0.63
    POSITIVE LOGITS
    လုံး
    0.83
    ANTE
    0.78
    Siehe
    0.77
     Aaj
    0.77
     bold
    0.75
    திலும்
    0.74
    エ
    0.73
    謗
    0.73
     abaixo
    0.72
    ante
    0.71
    Activations Density 0.064%

    No Known Activations