© 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-65K
    7. 8473
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuation or next steps

    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_65k_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
     primavera
    0.83
    aun
    0.83
     нови
    0.82
     Bitte
    0.81
    𝘽
    0.78
     signifie
    0.78
    مین
    0.78
    મને
    0.77
    迹
    0.77
    那么
    0.75
    POSITIVE LOGITS
    daemon
    0.82
    ি
    0.74
    ウェア
    0.70
     whole
    0.69
    Incoming
    0.68
     eighty
    0.68
    чо
    0.68
     participant
    0.67
     subsequent
    0.67
     radiologists
    0.67
    Activations Density 0.000%

    No Known Activations