© 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. 12-GEMMASCOPE-2-RES-262K
    7. 31667
    Prev
    Next
    INDEX
    Explanations

    landscape

    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_12_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
     snugly
    1.19
    iously
    1.16
    ções
    1.11
     appropriated
    1.03
     minced
    1.03
     immensely
    1.02
     simplifying
    0.99
     该
    0.98
    cknowled
    0.98
    RL
    0.96
    POSITIVE LOGITS
     große
    1.35
     pâle
    1.21
     andere
    1.19
     bekannte
    1.19
     totalement
    1.16
     postérieur
    1.16
     Worte
    1.16
     maak
    1.16
     letras
    1.14
     waren
    1.12
    Activations Density 0.012%

    No Known Activations