© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 6549
    Prev
    Next
    INDEX
    Explanations

    was, was, was

    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_262k_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
    /
    1.14
     &
    1.06
     potentially
    1.04
     will
    1.01
     potential
    1.01
     additional
    0.99
     dapat
    0.98
     may
    0.96
     provides
    0.93
    สามารถ
    0.91
    POSITIVE LOGITS
     médiocrement
    1.03
     vardı
    1.02
    鋃
    1.02
     aveva
    1.01
     είχε
    1.01
     lelaki
    1.01
    ontiti
    1.00
     murió
    0.98
     moglie
    0.98
     médecins
    0.97
    Activations Density 0.001%

    No Known Activations