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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4100
    Prev
    Next
    INDEX
    Explanations

    AI hallucinations

    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
    My
    0.75
    Your
    0.73
     моей
    0.69
    Moss
    0.69
     rains
    0.68
    夶
    0.68
    Ne
    0.68
     my
    0.67
     Pon
    0.66
    шер
    0.66
    POSITIVE LOGITS
     ideias
    0.73
     إ
    0.68
     ideia
    0.68
    intă
    0.67
     क्रमशः
    0.65
     elkaar
    0.65
     różnych
    0.65
    إ
    0.64
     Idee
    0.64
     idée
    0.64
    Activations Density 0.088%

    No Known Activations