© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4420
    Prev
    Next
    INDEX
    Explanations

    He followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     Với
    0.79
    Với
    0.69
    employed
    0.66
     Nhưng
    0.65
     Mỗi
    0.65
    patient
    0.64
    できない
    0.62
    淇
    0.59
    υνα
    0.59
    从事
    0.59
    POSITIVE LOGITS
     is
    0.73
     critères
    0.69
     data
    0.69
     oxidation
    0.67
     ook
    0.67
     är
    0.66
     criteria
    0.65
     invariant
    0.64
     criterio
    0.64
     salient
    0.63
    Activations Density 0.005%

    No Known Activations