© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3886
    Prev
    Next
    INDEX
    Explanations

    subject followed by should or must

    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_17_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
    ));
    0.69
    યા
    0.66
     различни
    0.65
     tantôt
    0.61
    တယ်။
    0.61
     Neste
    0.60
    வருக
    0.60
    TERY
    0.60
    λη
    0.60
    ))`
    0.59
    POSITIVE LOGITS
     should
    3.96
     Should
    3.55
    should
    3.44
    Should
    3.30
     shouldn
    3.06
     SHOULD
    3.01
     ought
    2.66
    应该
    2.64
     debería
    2.61
     sollte
    2.59
    Activations Density 0.503%

    No Known Activations