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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 190963
    Prev
    Next
    INDEX
    Explanations

    charging into action

    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_40_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
     छु
    0.49
    弱
    0.48
    Weak
    0.46
     weak
    0.46
     দুর্বল
    0.46
     ضع
    0.45
     Weak
    0.42
     débil
    0.42
    weak
    0.41
    烫
    0.41
    POSITIVE LOGITS
     charging
    0.74
    Charging
    0.68
    充電
    0.67
     Charging
    0.67
    charging
    0.64
     charged
    0.60
     charger
    0.59
    Charge
    0.58
     concentrating
    0.57
     stance
    0.57
    Activations Density 0.028%

    No Known Activations