© 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. 2503
    Prev
    Next
    INDEX
    Explanations

    content after prepositions

    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
     (?)
    0.96
     délégation
    0.92
    และ
    0.88
     სისტ
    0.87
    (?)
    0.87
    Ů
    0.87
    ům
    0.81
     jurídica
    0.81
     simplifié
    0.78
    /
    0.78
    POSITIVE LOGITS
     the
    1.09
     getting
    0.99
     attempting
    0.84
     دے
    0.84
    the
    0.83
     ש
    0.83
     any
    0.82
     adore
    0.80
     get
    0.80
    Whats
    0.80
    Activations Density 0.039%

    No Known Activations