© 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. 51051
    Prev
    Next
    INDEX
    Explanations

    increasing tension

    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
    pedido
    0.50
    ко
    0.46
    inplace
    0.45
    いただき
    0.45
    м
    0.45
     জানিয়ে
    0.43
    includes
    0.43
    🤌
    0.43
    AMPLES
    0.42
    ます
    0.42
    POSITIVE LOGITS
     increasing
    0.48
     الشباب
    0.47
     skyrocketing
    0.46
     Hypertension
    0.46
     Jugendliche
    0.45
     Youth
    0.44
     adolescence
    0.44
     obecnie
    0.44
     বর্তমানে
    0.44
     zunehm
    0.43
    Activations Density 0.002%

    No Known Activations