© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199902
    Prev
    Next
    INDEX
    Explanations

    non-explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     Arbitration
    0.47
    Game
    0.44
    ική
    0.44
    Antes
    0.43
    hled
    0.43
     língua
    0.43
    Online
    0.42
    紫
    0.42
    angé
    0.41
     вікі
    0.41
    POSITIVE LOGITS
     nanotubes
    0.50
     astronaut
    0.47
     nanot
    0.47
     macromolecules
    0.46
     fetus
    0.46
     training
    0.45
     phenomena
    0.44
     absorbance
    0.44
     carboxyl
    0.44
     nutrit
    0.44
    Activations Density 0.007%

    No Known Activations